Use cases › Doing things
Call tools and APIs
Models trained to emit structured function or tool calls so an application can execute them (function calling, MCP tools, agent actions).
Benchmarks that represent this job 6
A model's row on one of these third-party boards is what earns the measured label; the same benchmark name in the model's own card earns author-reported.
Models 288
Narrow by what you can run and pay for. Rows are ordered measured → author-reported → structural, then by watch-list score; click a column to re-sort. Every chip links to its source.
| Model | Evidence | Params | Context | Price from | Runs on | License | Providers | Measured latency |
|---|---|---|---|---|---|---|---|---|
| Llama-3.1-8B-Instruct meta-llama | measured BFCL 25.83tool calling at 1 provider | 8.03B | 128K | $0.02 | Single GPU | Llama 3.1 Community Licen… attribution | 4 | — |
| Llama-3.3-70B-Instruct meta-llama | measured BFCL 31.9tool calling at 3 providers | 70.6B | 128K | $0.10 | Multi-GPU node | Llama 3.3 Community Licen… attribution | 7 | — |
| Llama-3.2-3B-Instruct meta-llama | measured BFCL 21.95 | 3.21B | 128K | $0.05 | Single GPU | Llama 3.2 Community Licen… attribution | 4 | — |
| Qwen3-8B Qwen | measured BFCL 42.57decision-model estimate p=0.97 +1 | 8.19B | 40K | $0.07 | Single GPU | Apache 2.0 | 3 | — |
| Qwen3-14B Qwen | measured BFCL 41.03decision-model estimate p=0.87 +1 | 14.8B | 40K | $0.07 | Single high-end GPU | Apache 2.0 | 4 | — |
| gemma-3-4b-it google | measured BFCL 19.62tool calling at 1 provider | 4.30B | 128K | $0.04 | Single GPU | Gemma Terms of Use attribution | 4 | — |
| Qwen3-0.6B Qwen | measured BFCL 23.93decision-model estimate p=0.93 +1 | 752M | 40K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-32B Qwen | measured BFCL 48.71decision-model estimate p=0.92 +1 | 32.8B | 40K | $0.08 | Single high-end GPU | Apache 2.0 | 4 | — |
| gemma-3-27b-it google | measured BFCL 29.47tool calling at 1 provider | 27.4B | 128K | $0.08 | Single high-end GPU | Gemma Terms of Use attribution | 4 | — |
| Kimi-K2-Instruct moonshotai | measured BFCL 59.06decision-model estimate p=1.00 +1 | 1.03T | 128K | $0.57 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| phi-4 microsoft | measured BFCL 28.79 | 14.7B | 16K | $0.06 | Single high-end GPU | MIT | 3 | — |
| Llama-4-Scout-17B-16E-Instruct meta-llama | measured BFCL 28.13tool calling at 2 providers | 109B | 1.3M | $0.08 | Multi-GPU node | Llama Community License (… attribution | 4 | — |
| gemma-3-12b-it google | measured BFCL 30.43tool calling at 1 provider | 12.2B | 128K | $0.04 | Single high-end GPU | Gemma Terms of Use attribution | 3 | — |
| Qwen3-4B-Instruct-2507 Qwen | measured BFCL 35.68Author reports BFCL-v3 61.9 +1 | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 1 | — |
| gemma-3-1b-it google | measured BFCL 7.17 | 1000M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 1 | — |
| Qwen3-235B-A22B-Instruct-2507 Qwen | measured BFCL 52.15chat template: <tool_call> +1 | 235B (22B active) | 256K | $0.09 | Multi-GPU node | Apache 2.0 | 5 | — |
| Qwen3-1.7B Qwen | measured BFCL 28.41decision-model estimate p=0.94 +1 | 2.03B | 40K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-30B-A3B-Instruct-2507 Qwen | measured BFCL 41.39chat template: <tool_call> | 30.5B (3B active) | 256K | $0.09 | Single high-end GPU | Apache 2.0 | 2 | — |
| GLM-4.6 zai-org | measured BFCL 72.38decision-model estimate p=1.00 +1 | 357B | 198K | $0.40 | Cluster | MIT | 5 | — |
| DeepSeek-V3.2-Exp deepseek-ai | measured BFCL 54.12chat template: tool_calls | 685B | 160K | $0.27 | Cluster | MIT | 2 | — |
| Llama-xLAM-2-8b-fc-r Salesforce | measured BFCL 46.68decision-model estimate p=1.00 +1 | 8.03B | 128K | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| gemma-4-26B-A4B-it google | author-reported Author reports Tau2 (average over 3) 68.2%decision-model estimate p=1.00 +1 | 25.8B (4B active) | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 6 | 0.9 s · 51 tok/s |
| GLM-5.3 zai-org | author-reported Author reports Toolathlon Verified 73.0Author reports toolathlon_verified 73.0 +1 | 753B | 1M | $0.07 | Cluster | GLM License (glm-5.3) review | 9 | — |
| Kimi-K3 moonshotai | author-reported Author reports toolathlon_verified 76.5decision-model estimate p=0.92 +1 | 2.78T | 1M | $0.23 | Cluster | Kimi K3 (Modified MIT) (k… gated-threshold | 7 | 25.6 s · 59 tok/s |
| gemma-4-31B-it google | author-reported Author reports Tau2 (average over 3) 76.9%decision-model estimate p=0.99 +1 | 31.3B | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 5 | — |
| DeepSeek-V4-Flash-0731 deepseek-ai | author-reported Author reports Toolathlon-Verified 70.3decision-model estimate p=0.94 +1 | 304B | 1M | $0.04 | Cluster | MIT | 7 | 15.3 s · 122 tok/s |
| Kimi-K2.6 moonshotai | author-reported Author reports Toolathlon 50.0decision-model estimate p=0.89 +1 | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 5 | — |
| DeepSeek-R1-0528 deepseek-ai | author-reported Author reports BFCL_v3_MultiTurn (Acc) 37.0Author reports Tau-Bench (Pass@1) 63.9 +1 | 685B | 160K | $0.50 | Cluster | MIT | 4 | — |
| Qwen3-Next-80B-A3B-Instruct Qwen | author-reported Author reports BFCL-v3 70.3Author reports TAU2-Retail 57.3 +1 | 81.3B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| gemma-4-E4B-it google | author-reported Author reports Tau2 (average over 3) 42.2%decision-model estimate p=0.99 +1 | 8.00B | 128K | — | Single GPU | Apache 2.0 | 1 | — |
| DeepSeek-V4-Pro-0813 deepseek-ai | author-reported Author reports Toolathlon-Verified 74.1decision-model estimate p=0.98 +1 | 1.65T | 1M | $0.12 | Cluster | MIT | 6 | — |
| gemma-4-E2B-it google | author-reported Author reports Tau2 (average over 3) 24.5%decision-model estimate p=0.99 +1 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3-4B-Thinking-2507 Qwen | author-reported Author reports BFCL-v3 71.2Author reports TAU2-Airline 58.0 +1 | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| gemma-4-12B-it google | author-reported Author reports Tau2 (average over 3) 69.0%chat template: tool_calls | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| DeepSeek-V4-Flash-Vision-Exp deepseek-ai | author-reported Author reports Toolathlon-Verified 75.9decision-model estimate p=0.98 +1 | 305B | 1M | $0.22 | Cluster | MIT | 2 | — |
| diffusiongemma-26B-A4B-it google | author-reported Author reports Tau2 (average over 3) 56.2%chat template: tool_calls | 25.8B (4B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| gemma-4-31B google | author-reported Author reports Tau2 (average over 3) 76.9%decision-model estimate p=0.99 | 31.3B | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 1 | — |
| gemma-4-E4B google | author-reported Author reports Tau2 (average over 3) 42.2%decision-model estimate p=1.00 | 8.00B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| gemma-4-26B-A4B google | author-reported Author reports Tau2 (average over 3) 68.2%decision-model estimate p=0.99 | 25.8B (4B active) | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 2 | — |
| SmolLM3-3B HuggingFaceTB | author-reported Author reports BFCL 92.3chat template: <tool_call> | 3.08B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| NVIDIA-Nemotron-Nano-9B-v2 nvidia | author-reported Author reports BFCL v3 66.9%chat template: tool_calls | 8.89B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| Qwen3-235B-A22B-Thinking-2507 Qwen | author-reported Author reports BFCL-v3 71.9Author reports TAU2-Retail 71.9 +1 | 235B (22B active) | 256K | $0.23 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3-30B-A3B-Thinking-2507 Qwen | author-reported Author reports BFCL-v3 72.4Author reports TAU2-Retail 58.8 +1 | 30.5B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| gemma-4-E2B google | author-reported Author reports Tau2 (average over 3) 24.5%decision-model estimate p=1.00 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3-Next-80B-A3B-Thinking Qwen | author-reported Author reports BFCL-v3 72.0chat template: <tool_call> | 81.3B (3B active) | 256K | $0.15 | Multi-GPU node | Apache 2.0 | 1 | — |
| MiMo-V2.6-Pro-RL XiaomiMiMo | author-reported Author reports Toolathlon-Verified 76.9decision-model estimate p=0.96 +1 | 1.02T | 1M | $0.39 | Cluster | MIT | 2 | — |
| gemma-4-12B google | author-reported Author reports Tau2 (average over 3) 69.0% | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| MiMo-V2.6-Flash-RL XiaomiMiMo | author-reported Author reports Toolathlon-Verified 73.6decision-model estimate p=0.95 +1 | 311B | 1M | $0.09 | Cluster | MIT | 2 | — |
| Laguna-S-2.1 poolside | author-reported Author reports Toolathlon Verified 49.7%decision-model estimate p=0.99 +1 | 118B | 1M | $0.00 | Multi-GPU node | — review | 2 | — |
| gemma-4-31B-it-assistant google | author-reported Author reports Tau2 (average over 3) 76.9%decision-model estimate p=0.90 | 470M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Step-3.7-Flash stepfun-ai | author-reported Author reports Toolathlon 49.5decision-model estimate p=0.98 +1 | 201B | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| gemma-4-26B-A4B-it-assistant google | author-reported Author reports Tau2 (average over 3) 68.2%decision-model estimate p=0.92 | 420M (4B active) | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Llama-3.1-Nemotron-Nano-8B-v1 nvidia | author-reported Author reports BFCL v2 Live 63.9%decision-model estimate p=1.00 +1 | 8.03B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| functiongemma-270m-it google | author-reported Author reports BFCL Irrelevance 73.7decision-model estimate p=1.00 +1 | 268M | 32K | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| Ornith-1.5-9B ornith-ai | author-reported Author reports Toolathlon-Verified 41.2chat template: <tool_call> | 9.65B | 256K | — | Single GPU | MIT | 1 | — |
| Nanbeige4.1-3B Nanbeige | author-reported Author reports BFCL-V4 56.50Author reports Tau2-Bench 48.57 +1 | 3.93B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3.8-27B Qwen | structural decision-model estimate p=0.86chat template: <tool_call> +1 | 27.8B | 256K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 28.6 s · 87 tok/s |
| gpt-oss-120b openai | structural decision-model estimate p=1.00chat template: tool_calls +1 | 117B | 128K | $0.03 | Multi-GPU node | Apache 2.0 | 13 | 0.8 s · 168 tok/s |
| GLM-5.3-Flash zai-org | structural chat template: <tool_call>tool calling at 6 providers | 321B | 1M | $0.02 | Cluster | MIT | 9 | 8.1 s · 153 tok/s |
| gpt-oss-20b openai | structural decision-model estimate p=1.00chat template: tool_calls +1 | 20.9B | 128K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 2.8 s · 58 tok/s |
| GLM-5.2 zai-org | structural decision-model estimate p=0.76chat template: <tool_call> +1 | 753B | 1M | $0.03 | Cluster | MIT | 9 | — |
| DeepSeek-V4.1-Flash deepseek-ai | structural chat template: tool_callstool calling at 5 providers | 763B | 1M | $0.02 | Cluster | MIT | 8 | — |
| Qwen3.5-9B Qwen | structural chat template: <tool_call>tool calling at 3 providers | 9.65B | 256K | $0.08 | Single GPU | Apache 2.0 | 6 | 2.8 s · 117 tok/s |
| Qwen3.6-35B-A3B Qwen | structural decision-model estimate p=0.77chat template: <tool_call> +1 | 36.0B (3B active) | 256K | $0.05 | Multi-GPU node | Apache 2.0 | 5 | — |
| DeepSeek-V4-Pro deepseek-ai | structural tool calling at 2 providers | 1.60T | 1M | $0.21 | Cluster | MIT | 5 | — |
| DeepSeek-R1 deepseek-ai | structural chat template: tool_callstool calling at 1 provider | 684B | 160K | $0.70 | Cluster | MIT | 3 | — |
| GLM-4.7-Flash zai-org | structural chat template: <tool_call>tool calling at 3 providers | 31.2B | 198K | $0.06 | Single high-end GPU | MIT | 5 | — |
| Qwen3-VL-8B-Instruct Qwen | structural decision-model estimate p=0.94chat template: <tool_call> | 8.77B | 256K | $0.25 | Single GPU | Apache 2.0 | 4 | — |
| Qwen3.5-397B-A17B Qwen | structural decision-model estimate p=0.90chat template: <tool_call> +1 | 403B (17B active) | 256K | $0.39 | Cluster | Apache 2.0 | 7 | — |
| Qwen2.5-7B-Instruct Qwen | structural chat template: <tool_call> | 7.62B | 32K | $0.10 | Single GPU | Apache 2.0 | 3 | — |
| MiniMax-M3 MiniMaxAI | structural decision-model estimate p=0.92tag: agent +1 | 427B | 1M | $0.22 | Cluster | MiniMax Model License (mi… gated-threshold | 7 | — |
| DeepSeek-V4-Flash deepseek-ai | structural tool calling at 1 provider | 291B | 1M | $0.03 | Cluster | MIT | 4 | — |
| Qwen3.6-27B Qwen | structural chat template: <tool_call>tool calling at 2 providers | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| Kimi-K2.5 moonshotai | structural decision-model estimate p=0.99chat template: tool_calls +1 | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| Qwen2.5-Coder-32B-Instruct Qwen | structural chat template: <tool_call> | 32.8B | 32K | $0.06 | Single high-end GPU | Apache 2.0 | 4 | — |
| GLM-5 zai-org | structural decision-model estimate p=0.95chat template: <tool_call> +1 | 754B | 198K | $0.60 | Cluster | MIT | 5 | — |
| Qwen3.5-35B-A3B Qwen | structural chat template: <tool_call>tool calling at 2 providers | 36.0B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| Qwen3.8-Flash-Next Qwen | structural chat template: <tool_call> | 180B | 256K | $0.15 | Multi-GPU node | Qwen License (qwen-commun… gated-threshold | 2 | — |
| Qwen3.5-27B Qwen | structural decision-model estimate p=0.74chat template: <tool_call> +1 | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| MiniMax-M2.5 MiniMaxAI | structural chat template: tool_callstool calling at 1 provider | 229B | 192K | $0.27 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 4 | — |
| Qwen3-235B-A22B Qwen | structural decision-model estimate p=0.93chat template: <tool_call> +1 | 235B (22B active) | 40K | $0.20 | Multi-GPU node | Apache 2.0 | 4 | — |
| DeepSeek-V4.1-Flash-1017 deepseek-ai | structural tool calling at 4 providers | 763B | 1M | $0.20 | Cluster | MIT | 4 | — |
| Qwen3-Coder-30B-A3B-Instruct Qwen | structural decision-model estimate p=0.99chat template: <tool_call> | 30.5B (3B active) | 256K | $0.07 | Single high-end GPU | Apache 2.0 | 3 | — |
| Qwen3.5-4B Qwen | structural chat template: <tool_call> | 4.66B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen2.5-1.5B-Instruct Qwen | structural chat template: <tool_call> | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-VL-30B-A3B-Instruct Qwen | structural decision-model estimate p=0.87chat template: <tool_call> +1 | 31.1B (3B active) | 256K | $0.15 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3-Embedding-0.6B Qwen | structural chat template: <tool_call> | 596M | 32K | $0.01 | Laptop / edge | Apache 2.0 | 1 | — |
| DeepSeek-V3 deepseek-ai | structural chat template: tool_callstool calling at 1 provider | 684B | 160K | $0.26 | Cluster | Not declared review | 2 | — |
| GLM-5.1 zai-org | structural decision-model estimate p=0.98chat template: <tool_call> +1 | 754B | 198K | $0.96 | Cluster | MIT | 4 | — |
| Qwen2.5-VL-7B-Instruct Qwen | structural decision-model estimate p=0.94 | 8.29B | 125K | — | Single GPU | Apache 2.0 | 1 | — |
| DeepSeek-V3-0324 deepseek-ai | structural chat template: tool_callstool calling at 1 provider | 685B | 160K | $0.24 | Cluster | MIT | 3 | — |
| GLM-4.5-Air zai-org | structural decision-model estimate p=1.00chat template: <tool_call> +1 | 110B | 128K | $0.13 | Multi-GPU node | MIT | 4 | — |
| MiniMax-M2.7 MiniMaxAI | structural chat template: tool_callstool calling at 1 provider | 229B | 200K | $0.21 | Multi-GPU node | other review | 4 | — |
| Qwen2.5-3B-Instruct Qwen | structural chat template: <tool_call> | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen2.5-0.5B-Instruct Qwen | structural chat template: <tool_call> | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-4B Qwen | structural decision-model estimate p=0.90chat template: <tool_call> | 4.02B | 40K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Embedding-8B Qwen | structural chat template: <tool_call> | 7.57B | 40K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| DeepSeek-V3.2 deepseek-ai | structural decision-model estimate p=0.81tool calling at 1 provider | 685B | 160K | $0.21 | Cluster | MIT | 2 | — |
| Qwen2.5-Coder-7B-Instruct Qwen | structural chat template: <tool_call> | 7.62B | 32K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-Coder-Next Qwen | structural decision-model estimate p=0.94chat template: <tool_call> | 79.7B | 256K | $0.12 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3-VL-4B-Instruct Qwen | structural decision-model estimate p=0.94chat template: <tool_call> | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-30B-A3B Qwen | structural decision-model estimate p=0.89chat template: <tool_call> +1 | 30.5B (3B active) | 40K | $0.12 | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen2.5-VL-3B-Instruct Qwen | structural decision-model estimate p=0.93 | 3.75B | 125K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen3-VL-2B-Instruct Qwen | structural decision-model estimate p=0.78chat template: <tool_call> | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-72B-Instruct Qwen | structural chat template: <tool_call>tool calling at 1 provider | 72.7B | 32K | $0.36 | Multi-GPU node | Qwen License (qwen) gated-threshold | 3 | — |
| GLM-4.7 zai-org | structural decision-model estimate p=0.94chat template: <tool_call> +1 | 358B | 198K | $0.32 | Cluster | MIT | 4 | — |
| Qwen3-Reranker-0.6B Qwen | structural chat template: <tool_call> | 596M | 40K | $0.01 | Laptop / edge | Apache 2.0 | 2 | — |
| DeepSeek-R1-Distill-Qwen-32B deepseek-ai | structural chat template: tool_calls | 32.8B | 128K | — | Single high-end GPU | MIT | 2 | — |
| DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai | structural chat template: tool_calls | 1.78B | 128K | — | Single GPU | MIT | 1 | — |
| DeepSeek-R1-Distill-Qwen-7B deepseek-ai | structural chat template: tool_calls | 7.62B | 128K | $0.15 | Single GPU | MIT | 2 | — |
| Qwen3.5-122B-A10B Qwen | structural chat template: <tool_call>tool calling at 2 providers | 125B (10B active) | 256K | $0.26 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen2.5-VL-72B-Instruct Qwen | structural decision-model estimate p=0.77 | 73.4B | 125K | $0.80 | Multi-GPU node | Qwen License (qwen) gated-threshold | 3 | — |
| Muse-Glimmer-30B meta-models | structural decision-model estimate p=1.00chat template: tool_calls +1 | 29.8B | 128K | $0.30 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen2.5-0.5B Qwen | structural chat template: <tool_call> | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3.5-2B Qwen | structural chat template: <tool_call> | 2.27B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| MiniMax-M2 MiniMaxAI | structural chat template: tool_calls | 229B | 192K | $0.26 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-VL-235B-A22B-Instruct Qwen | structural decision-model estimate p=0.97chat template: <tool_call> +1 | 236B (22B active) | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3.5-0.8B Qwen | structural chat template: <tool_call> | 873M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-VL-32B-Instruct Qwen | structural decision-model estimate p=0.78 | 33.5B | 125K | — | Multi-GPU node | Apache 2.0 | 2 | — |
| Kimi-K2.7-Code moonshotai | structural decision-model estimate p=0.82chat template: tool_calls +1 | 1.03T | 256K | $0.67 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| DeepSeek-R1-Distill-Qwen-14B deepseek-ai | structural chat template: tool_calls | 14.8B | 128K | $0.20 | Single high-end GPU | MIT | 2 | — |
| Step-3.5-Flash stepfun-ai | structural decision-model estimate p=0.74chat template: <tool_call> | 199B | 256K | $0.10 | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-R1-Distill-Llama-8B deepseek-ai | structural chat template: tool_calls | 8.03B | 128K | $0.05 | Single GPU | MIT | 2 | — |
| Inkling thinkingmachines | structural chat template: tool_callstool calling at 3 providers | 952B | 1M | $0.00 | Cluster | Apache 2.0 | 4 | — |
| Qwen3.8-2.4T-A95B Qwen | structural decision-model estimate p=0.86chat template: <tool_call> +1 | 2.45T (95B active) | 256K | $2.00 | Cluster | Qwen License (qwen3.8-max) gated-threshold | 5 | — |
| Qwen3-VL-Embedding-2B Qwen | structural chat template: <tool_call> | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| UI-TARS-1.5-7B ByteDance-Seed | structural chat template: <tool_call> | 8.29B | 125K | $0.10 | Single GPU | Apache 2.0 | 3 | — |
| Qwen3-Embedding-4B Qwen | structural chat template: <tool_call> | 4.02B | 40K | $0.02 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Reranker-4B Qwen | structural chat template: <tool_call> | 4.02B | 40K | $0.03 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Coder-480B-A35B-Instruct Qwen | structural decision-model estimate p=1.00chat template: <tool_call> | 480B (35B active) | 256K | $0.22 | Cluster | Apache 2.0 | 3 | — |
| DeepSeek-R1-Distill-Llama-70B deepseek-ai | structural chat template: tool_calls | 70.6B | 128K | — | Multi-GPU node | MIT | 2 | — |
| Qwen2.5-14B-Instruct Qwen | structural chat template: <tool_call> | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Kimi-K2-Thinking moonshotai | structural decision-model estimate p=1.00chat template: tool_calls | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| Qwen2.5-32B-Instruct Qwen | structural chat template: <tool_call> | 32.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| DeepSeek-R1-0528-Qwen3-8B deepseek-ai | structural chat template: tool_calls | 8.19B | 128K | — | Single GPU | MIT | 1 | — |
| QwQ-32B Qwen | structural chat template: <tool_call> | 32.8B | 40K | — | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-14B-Instruct Qwen | structural chat template: <tool_call> | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen3-VL-32B-Instruct Qwen | structural decision-model estimate p=0.85chat template: <tool_call> | 33.4B | 256K | — | Multi-GPU node | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-7B Qwen | structural chat template: <tool_call> | 7.62B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Hy3 tencent | structural decision-model estimate p=0.72chat template: tool_calls +1 | 299B | 256K | $0.08 | Cluster | Apache 2.0 | 3 | — |
| GLM-4.5 zai-org | structural decision-model estimate p=1.00chat template: <tool_call> | 358B | 128K | $0.60 | Cluster | MIT | 2 | — |
| Qwen3-VL-Embedding-8B Qwen | structural chat template: <tool_call> | 8.14B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2.5-7B Qwen | structural chat template: <tool_call> | 7.62B | 128K | $0.10 | Single GPU | Apache 2.0 | 1 | — |
| Kimi-K2-Instruct-0905 moonshotai | structural chat template: tool_callstool calling at 1 provider | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| MiniMax-M2.1 MiniMaxAI | structural chat template: tool_calls | 229B | 192K | $0.30 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-VL-235B-A22B-Thinking Qwen | structural decision-model estimate p=0.97chat template: <tool_call> | 236B (22B active) | 256K | — | Multi-GPU node | Apache 2.0 | 3 | — |
| GLM-4.5V zai-org | structural chat template: <tool_call>tool calling at 2 providers | 108B | 64K | $0.60 | Multi-GPU node | MIT | 3 | — |
| Qwen2.5-1.5B Qwen | structural chat template: <tool_call> | 1.54B | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| LocateAnything-3B nvidia | structural chat template: <tool_call> | 3.83B | 32K | — | Single GPU | NVIDIA Open Model License… attribution | 0 | — |
| Qwen3-0.6B-Base Qwen | structural chat template: <tool_call> | 596M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Phi-4-mini-instruct microsoft | structural decision-model estimate p=0.96chat template: <|tool|> | 3.84B | 128K | — | Single GPU | MIT | 0 | — |
| Qwen3-4B-Base Qwen | structural chat template: <tool_call> | 4.02B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-Coder-3B-Instruct Qwen | structural chat template: <tool_call> | 3.09B | 32K | $0.01 | Single GPU | Qwen License (qwen-resear… gated-threshold | 2 | — |
| Qwen3-Reranker-8B Qwen | structural chat template: <tool_call> | 8.19B | 40K | $0.05 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-8B-Base Qwen | structural chat template: <tool_call> | 8.19B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-VL-8B-Thinking Qwen | structural decision-model estimate p=0.86chat template: <tool_call> | 8.77B | 256K | — | Single GPU | Apache 2.0 | 3 | — |
| QwQ-32B-Preview Qwen | structural chat template: <tool_call> | 32.8B | 32K | — | Single high-end GPU | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-1.5B-Instruct Qwen | structural chat template: <tool_call> | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Hermes-3-Llama-3.1-8B NousResearch | structural decision-model estimate p=1.00chat template: <tool_call> | 8.03B | 128K | — | Single GPU | Llama 3 Community License attribution | 1 | — |
| Qwen2.5-7B-Instruct-1M Qwen | structural chat template: <tool_call> | 7.62B | 986K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-3B Qwen | structural chat template: <tool_call> | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Apertus-8B-Instruct-2509 swiss-ai | structural decision-model estimate p=0.93chat template: tool_calls | 8.05B | 64K | $0.10 | Single GPU | Apache 2.0 | 2 | — |
| GLM-4.6V-Flash zai-org | structural decision-model estimate p=1.00chat template: <tool_call> +1 | 10.3B | 128K | $0.30 | Single high-end GPU | MIT | 2 | — |
| Qwen2.5-Coder-1.5B Qwen | structural chat template: <tool_call> | 1.54B | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen3-1.7B-Base Qwen | structural chat template: <tool_call> | 1.72B | 32K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2.5-Coder-0.5B-Instruct Qwen | structural chat template: <tool_call> | 494M | 32K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-Math-1.5B Qwen | structural decision-model estimate p=0.70chat template: <tool_call> | 1.54B | 4K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Kimi-Linear-48B-A3B-Instruct moonshotai | structural chat template: tool_calls | 49.1B (3B active) | — | — | Multi-GPU node | MIT | 1 | — |
| LFM2.5-2.6B LiquidAI | structural decision-model estimate p=0.96chat template: tool_calls | 2.70B | 128K | $0.00 | Single GPU | lfm1.0 review | 1 | — |
| Llama-3.1-Nemotron-70B-Instruct-HF nvidia | structural chat template: tool_calls | 70.6B | 128K | — | Multi-GPU node | Llama 3.1 Community Licen… attribution | 1 | — |
| LFM2.5-1.2B-Instruct LiquidAI | structural chat template: tool_calls | 1.17B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| chandra-ocr-2 datalab-to | structural chat template: <tool_call> | 5.30B | 256K | — | Single GPU | OpenRAIL attribution | 0 | — |
| Qwen2.5-14B Qwen | structural chat template: <tool_call> | 14.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| MiniCPM5-2B openbmb | structural decision-model estimate p=1.00tag: tool-calling +1 | 2.52B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Hy4-preview tencent | structural chat template: tool_callstool calling at 2 providers | 780B | 1M | $0.75 | Cluster | Apache 2.0 | 3 | — |
| Qwen3-VL-4B-Thinking Qwen | structural decision-model estimate p=0.85chat template: <tool_call> | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen2.5-32B Qwen | structural chat template: <tool_call> | 32.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Inkling-Small thinkingmachines | structural chat template: tool_callstool calling at 1 provider | 266B | 1M | $0.00 | Multi-GPU node | Apache 2.0 | 2 | — |
| Ornith-1.0-9B ornith-ai | structural chat template: <tool_call> | 1.47M | 256K | — | Laptop / edge | MIT | 1 | — |
| Qwen3-VL-30B-A3B-Thinking Qwen | structural decision-model estimate p=0.91chat template: <tool_call> | 31.1B (3B active) | 256K | $0.29 | Single high-end GPU | Apache 2.0 | 2 | — |
| GLM-4.6V zai-org | structural decision-model estimate p=1.00chat template: <tool_call> +1 | 108B | 128K | $0.30 | Multi-GPU node | MIT | 3 | — |
| gpt-oss-safeguard-20b openai | structural chat template: tool_callstool calling at 1 provider | 21.5B | 128K | $0.07 | Single high-end GPU | Apache 2.0 | 2 | — |
| MiniCPM-o-4_5 openbmb | structural chat template: <tool_call> | 9.37B | 40K | — | Single GPU | Apache 2.0 | 0 | — |
| MiMo-V2.5 XiaomiMiMo | structural decision-model estimate p=0.91tag: agent +1 | 311B | 1M | $0.12 | Cluster | MIT | 2 | — |
| Kimi-VL-A3B-Instruct moonshotai | structural decision-model estimate p=0.72tag: agent | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| LFM2.5-8B-A1B LiquidAI | structural decision-model estimate p=0.95chat template: tool_calls | 8.47B (1B active) | 125K | — | Single GPU | lfm1.0 review | 0 | — |
| MiMo-V2.5-Pro XiaomiMiMo | structural decision-model estimate p=0.97tag: agent +1 | 1.02T | 1M | $0.30 | Cluster | MIT | 2 | — |
| Qwen2.5-Math-1.5B-Instruct Qwen | structural decision-model estimate p=0.78chat template: <tool_call> | 1.54B | 4K | — | Laptop / edge | Apache 2.0 | 1 | — |
| MiniCPM5-1B openbmb | structural decision-model estimate p=1.00tag: tool-calling +1 | 1.08B | 128K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen3-14B-Base Qwen | structural chat template: <tool_call> | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Ling-3.0-flash inclusionAI | structural decision-model estimate p=0.81chat template: <tool_call> +1 | 127B | 256K | $0.02 | Multi-GPU node | MIT | 3 | — |
| Qwen2.5-Math-7B Qwen | structural decision-model estimate p=0.78chat template: <tool_call> | 7.62B | 4K | — | Single GPU | Apache 2.0 | 1 | — |
| MiniCPM-o-2_6 openbmb | structural chat template: <tool_call> | 8.67B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Jackrong | structural chat template: <tool_call> | 27.8B | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| MiniMax-M3.1-Flash MiniMaxAI | structural tag: agenttool calling at 1 provider | 220B | 977K | $0.15 | Multi-GPU node | MiniMax Model License (mi… gated-threshold | 1 | — |
| Qwen3.5-0.8B-Base Qwen | structural chat template: <tool_call> | 873M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Qwen2.5-Math-7B-Instruct Qwen | structural decision-model estimate p=0.76chat template: <tool_call> | 7.62B | 4K | — | Single GPU | Apache 2.0 | 1 | — |
| MiniCPM-V-4.6 openbmb | structural chat template: <tool_call> | 1.30B | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Ornith-1.0-35B ornith-ai | structural chat template: <tool_call> | 665K | 256K | — | Laptop / edge | MIT | 0 | — |
| granite-4.1-8b ibm-granite | structural decision-model estimate p=1.00chat template: <tool_call> | 8.79B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| OvisOCR2 ATH-MaaS | structural chat template: <tool_call> | 853M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-Coder-3B Qwen | structural chat template: <tool_call> | 3.09B | 32K | — | Single GPU | Qwen License (qwen-resear… gated-threshold | 1 | — |
| Qwen2.5-14B-Instruct-1M Qwen | structural chat template: <tool_call> | 14.8B | 986K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| granite-4.1-3b ibm-granite | structural decision-model estimate p=1.00chat template: <tool_call> | 3.40B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3.5-4B-Base Qwen | structural chat template: <tool_call> | 4.66B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Llama-3.2-1B-Instruct unsloth | structural chat template: tool_calls | 1.24B | 128K | — | Laptop / edge | Llama 3.2 Community Licen… attribution | 0 | — |
| DeepSeek-V3.1-Base deepseek-ai | structural decision-model estimate p=0.99chat template: tool_calls | 685B | 160K | — | Cluster | MIT | 0 | — |
| Phi-4-mini-reasoning microsoft | structural chat template: <|tool|> | 3.84B | 128K | — | Single GPU | MIT | 1 | — |
| Olmo-3-7B-Instruct allenai | structural chat template: tool_calls | 7.30B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-350M LiquidAI | structural chat template: tool_calls | 354M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| Qwen3.5-9B-Base Qwen | structural chat template: <tool_call> | 9.65B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Meta-Llama-3.1-8B-Instruct unsloth | structural chat template: tool_calls | 8.03B | 128K | — | Single GPU | Llama 3.1 Community Licen… attribution | 1 | — |
| Llama-3_3-Nemotron-Super-49B-v1_5 nvidia | structural decision-model estimate p=1.00chat template: tool_calls | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| NVLM-D-72B nvidia | structural chat template: <tool_call> | 79.4B | — | — | Multi-GPU node | CC BY-NC 4.0 non-commercial | 0 | — |
| Qwen-AgentWorld-35B-A3B Qwen | structural decision-model estimate p=0.81tag: agent +1 | 34.7B (3B active) | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| tiny-Qwen2ForCausalLM-2.5 trl-internal-testing | structural chat template: <tool_call> | 2.44M | 32K | — | Laptop / edge | Not declared review | 0 | — |
| Qwen3.5-2B-Base Qwen | structural chat template: <tool_call> | 2.27B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| DeepSeek-R1-Zero deepseek-ai | structural chat template: tool_calls | 684B | 160K | — | Cluster | MIT | 0 | — |
| MiniCPM-V-4_5 openbmb | structural chat template: <tool_call> | 8.70B | 40K | — | Single GPU | Apache 2.0 | 0 | — |
| GLM-4-32B-0414 zai-org | structural decision-model estimate p=1.00chat template: tools | 32.6B | 32K | — | Single high-end GPU | MIT | 1 | — |
| InternVL3-78B OpenGVLab | structural decision-model estimate p=0.88 | 78.4B | — | — | Multi-GPU node | Qwen License (qwen) gated-threshold | 0 | — |
| MiMo-V2-Flash XiaomiMiMo | structural chat template: <tool_call> | 310B | 256K | — | Cluster | MIT | 0 | — |
| Nanbeige4.2-3B Nanbeige | structural decision-model estimate p=0.98chat template: <tool_call> | 4.17B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2-1.2B LiquidAI | structural chat template: tool_calls | 1.17B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| granite-4.2-8b ibm-granite | structural decision-model estimate p=1.00tag: tool-calling +1 | 8.79B | 128K | $0.06 | Single GPU | Apache 2.0 | 2 | — |
| LFM2.5-230M LiquidAI | structural decision-model estimate p=0.83chat template: tool_calls | 230M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| ERNIE-4.5-21B-A3B-Thinking baidu | structural chat template: <tool_call> | 21.8B (3B active) | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| LFM2.5-VL-450M LiquidAI | structural decision-model estimate p=0.99chat template: tool_calls | 449M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| DeepSeek-V2.5 deepseek-ai | structural chat template: tool_calls | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Llama-3_3-Nemotron-Super-49B-v1 nvidia | structural decision-model estimate p=1.00 | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| Hermes-3-Llama-3.1-405B NousResearch | structural decision-model estimate p=1.00chat template: <tool_call> | 406B | 128K | $1.00 | Cluster | Llama 3 Community License attribution | 2 | — |
| North-Mini-Code-1.0 CohereLabs | structural tag: agentchat template: tool_calls | 30.5B | 488K | $0.00 | Single high-end GPU | Apache 2.0 | 1 | — |
| Nemotron-Cascade-2-30B-A3B nvidia | structural chat template: <tool_call> | 31.6B (3B active) | 256K | — | Single high-end GPU | NVIDIA Open Model License… attribution | 0 | — |
| granite-4.0-h-tiny ibm-granite | structural decision-model estimate p=1.00chat template: <tool_call> | 6.94B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Bielik-11B-v3.0-Instruct speakleash | structural tool calling at 1 provider | 11.2B | — | $0.40 | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen3-VL-2B-Thinking Qwen | structural decision-model estimate p=0.82chat template: <tool_call> | 2.13B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Step3-VL-10B stepfun-ai | structural chat template: <tool_call> | 10.2B | 64K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| c4ai-command-r7b-12-2024 CohereLabs | structural tool calling at 1 provider | 8.03B | — | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| MiniMax-Text-01 MiniMaxAI | structural chat template: tools | 456B | 9.8M | $0.20 | Cluster | Not declared review | 1 | — |
| Ornith-1.5-35B-A3B ornith-ai | structural decision-model estimate p=0.78chat template: <tool_call> | 36.0B (3B active) | 256K | — | Multi-GPU node | MIT | 0 | — |
| MiniMax-M1-80k MiniMaxAI | structural chat template: tool_callstool calling at 1 provider | 456B | 9.8M | $0.55 | Cluster | Apache 2.0 | 1 | — |
| MiniMax-VL-01 MiniMaxAI | structural chat template: tools | 456B | 8K | — | Cluster | Not declared review | 0 | — |
| Solar-Open-100B upstage | structural chat template: tool_calls | 103B | 128K | — | Multi-GPU node | upstage-solar-license review | 0 | — |
| Hermes-3-Llama-3.1-70B NousResearch | structural decision-model estimate p=1.00chat template: <tool_call> | 70.6B | 128K | $0.70 | Multi-GPU node | Llama 3 Community License attribution | 3 | — |
| Fara-7B microsoft | structural decision-model estimate p=1.00 | 8.29B | 125K | — | Single GPU | MIT | 0 | — |
| SmolLM2-360M HuggingFaceTB | structural decision-model estimate p=0.89 | 362M | 8K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Olmo-3-7B-Think allenai | structural chat template: functions. | 7.30B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| LFM2.5-VL-1.6B LiquidAI | structural chat template: tools | 1.60B | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| EXAONE-4.5-33B LGAI-EXAONE | structural chat template: <tool_call> | 34.4B | 256K | — | Multi-GPU node | exaone review | 0 | — |
| Hy3-preview tencent | structural decision-model estimate p=0.79chat template: <tool_call> | 299B | 256K | $0.18 | Cluster | Other review | 1 | — |
| granite-4.0-h-small ibm-granite | structural decision-model estimate p=1.00chat template: <tool_call> | 32.2B | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| InternVL3-8B OpenGVLab | structural decision-model estimate p=0.87 | 7.94B | — | — | Single GPU | Apache 2.0 (qwen) | 0 | — |
| MiMo-7B-RL XiaomiMiMo | structural chat template: <tool_call> | 7.83B | 32K | — | Single GPU | MIT | 0 | — |
| granite-3.3-8b-instruct ibm-granite | structural decision-model estimate p=0.91chat template: <|tool_call|> | 8.17B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| InternVL3-1B OpenGVLab | structural decision-model estimate p=0.81 | 938M | — | — | Laptop / edge | Apache 2.0 (qwen) | 0 | — |
| K-EXAONE-236B-A23B LGAI-EXAONE | structural decision-model estimate p=0.96chat template: <tool_call> | 237B (23B active) | 256K | — | Multi-GPU node | k-exaone review | 0 | — |
| Intern-Decision-4B internlm | structural chat template: <tool_call> | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-0.8B internlm | structural chat template: <tool_call> | 853M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Winnow-12B EldanRing | structural chat template: tool_calls | — | 256K | — | — | Apache 2.0 | 0 | — |
| JevK5 alibiserikbay | structural chat template: <tool_call> | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-2B internlm | structural chat template: <tool_call> | 2.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Tev1-4B-experimental togethercomputer | structural chat template: <tool_call>tool calling at 1 provider | 4.66B | 256K | $0.04 | Single GPU | Not declared review | 1 | — |
| Tev1-0.8B-experimental togethercomputer | structural chat template: <tool_call> | 873M | 256K | — | Laptop / edge | Not declared review | 0 | — |
| xor juspay | structural chat template: <tool_call> | 35.1B | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| LFM2.5-350M-RLCD notnotsamuel | structural chat template: tool_calls | 354M | 125K | — | Laptop / edge | lfm1.0 review | 0 | — |
| openjev openjev | structural chat template: <tool_call> | 27.4B | 256K | — | Single high-end GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| Jev-Omni akhilaaa3 | structural chat template: tool_calls | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| JEV-27B autotrust | structural chat template: <tool_call> | 26.9B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| pplx-decider-v1-27b perplexity-ai | structural chat template: <tool_call> | 26.1B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| Bespoke-Nimble-9B bespokelabs | structural chat template: <tool_call> | — | — | — | — | Apache 2.0 | 0 | — |
| kev-9b jaredpalmer | structural chat template: <tool_call> | — | — | — | — | Apache 2.0 | 0 | — |
| lev interfaze-ai | structural chat template: <tool_call> | — | — | — | — | Apache 2.0 | 0 | — |
| decider-2b Mapika | structural chat template: <tool_call> | 1.88B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| decider-4b Mapika | structural chat template: <tool_call> | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| jpt-4b kirp | structural chat template: <tool_call> | 4.54B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| LFM2.5-2.6B-RLCD monotykamary | structural chat template: tool_calls | 2.70B | 128K | — | Single GPU | lfm1.0 review | 0 | — |
| system-one-qwen3.5-4b-scorer-v2b pngwn | structural chat template: <tool_call> | — | — | — | — | CC BY-NC 4.0 non-commercial | 0 | — |
| this-that-model-1.0 flock-io | structural chat template: <tool_call> | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| decider-35b-a3b-nvfp4 Mapika | structural chat template: <tool_call> | 17.9B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| metask-jev-4b-policy-mix wayfind | structural chat template: <tool_call> | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Bespoke-Nimble-9B-v2 bespokelabs | structural chat template: <tool_call> | — | — | — | — | Apache 2.0 | 0 | — |
| NeoHorse-Jev-4B TokenRhythm | structural tag: agentic | — | — | — | — | Apache 2.0 | 0 | — |
| this-that-model-1.2 flock-io | structural chat template: <tool_call> | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| Eikos-27B-FP8 caiovicentino1 | structural chat template: <tool_call> | 27.8B | 256K | — | Single high-end GPU | MIT | 0 | — |
| blink-27b thegovind | structural chat template: <tool_call> | 26.9B | 256K | — | Single high-end GPU | Research / non-commercial… non-commercial | 0 | — |
| jpt-0.8b kirp | structural chat template: <tool_call> | 853M | 256K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 0 | — |
| jpt-9b kirp | structural chat template: <tool_call> | 9.41B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| jebadiah-27b frontier-infra | structural chat template: <tool_call> | 27.8B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
No model matches every constraint. Loosen one, or switch the evidence filter back to any.
How to read this
- measured a third-party leaderboard row for this model. Settings (agent harness, edit format, prompt) differ between boards; compare within a benchmark, not across.
- author-reported a number the model author published in the card or eval files. Not reproduced by us.
- structural a deterministic signal from the name, config or chat template, or a decision-model estimate. A weak signal: it says the model was built or tagged for the job, not how well it does it. "decision-model estimate" chips are a probability from the Jev decision model, not a measurement.
- Runs on is the memory class of the BF16 weights (method); choosing a class shows that class and smaller. Quantized builds may fit a class lower.
- Price from is the cheapest observed hosted input price, USD per million tokens; models with no observed price are hidden when a ceiling is set. License friction: permissive = none or attribution-only; high = non-commercial.
- Ordering within a tier is the watch-list score (Hub likes, downloads, recency), not a quality verdict.
Subscribe
Follow "Call tools and APIs"
- /feeds/for/tool-use.xml(RSS 2.0) · one item per model with measured or author-reported evidence for this job
- /feeds/for/tool-use.json(JSON Feed 1.1) · same items, JSON Feed
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.