Use cases › Size of input
Read long documents
Models with a native context window of 128k tokens or more, for whole-repository, whole-book or many-document prompts.
Benchmarks that represent this job 8
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.
RULERLongBench v2Needle in a HaystackMRCRLongBenchHELMETInfiniteBenchAA-LCR
Models 241
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 |
|---|---|---|---|---|---|---|---|---|
| gemma-4-26B-A4B-it google | author-reported Author reports MRCR v2 8 needle 128k (average) 44.1%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 |
| Kimi-K3 moonshotai | author-reported Author reports AA-LCR 74.7decision-model estimate p=1.00 +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 MRCR v2 8 needle 128k (average) 66.4%decision-model estimate p=0.99 +1 | 31.3B | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 5 | — |
| DeepSeek-V4.1-Flash deepseek-ai | author-reported Author reports LongBench-V2 (EM) 45.2decision-model estimate p=1.00 +1 | 763B | 1M | $0.02 | Cluster | MIT | 8 | — |
| Qwen3.5-9B Qwen | author-reported Author reports AA-LCR 63.0decision-model estimate p=1.00 +1 | 9.65B | 256K | $0.08 | Single GPU | Apache 2.0 | 6 | 2.8 s · 117 tok/s |
| DeepSeek-V4-Pro deepseek-ai | author-reported Author reports LongBench-V2 (EM) 51.5decision-model estimate p=1.00 +1 | 1.60T | 1M | $0.21 | Cluster | MIT | 5 | — |
| Qwen3.5-397B-A17B Qwen | author-reported Author reports AA-LCR 68.7decision-model estimate p=0.82 +1 | 403B (17B active) | 256K | $0.39 | Cluster | Apache 2.0 | 7 | — |
| DeepSeek-V4-Flash deepseek-ai | author-reported Author reports LongBench-V2 (EM) 44.7decision-model estimate p=1.00 +1 | 291B | 1M | $0.03 | Cluster | MIT | 4 | — |
| Qwen3.5-35B-A3B Qwen | author-reported Author reports AA-LCR 58.5config: 262,144 context | 36.0B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| Qwen3.5-27B Qwen | author-reported Author reports AA-LCR 66.1Author reports LongBench v2 60.6 +1 | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| Qwen3.5-4B Qwen | author-reported Author reports AA-LCR 57.0decision-model estimate p=1.00 +1 | 4.66B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3.5-122B-A10B Qwen | author-reported Author reports AA-LCR 66.9Author reports LongBench v2 60.2 +1 | 125B (10B active) | 256K | $0.26 | Multi-GPU node | Apache 2.0 | 3 | — |
| Muse-Glimmer-30B meta-models | author-reported Author reports AA-LCR 80.0config: 131,072 context | 29.8B | 128K | $0.30 | Single high-end GPU | Apache 2.0 | 4 | — |
| gemma-4-E2B-it google | author-reported Author reports MRCR v2 8 needle 128k (average) 19.1%decision-model estimate p=0.99 +1 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| gemma-4-12B-it google | author-reported Author reports MRCR v2 8 needle 128k (average) 43.4%decision-model estimate p=1.00 +1 | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| diffusiongemma-26B-A4B-it google | author-reported Author reports MRCR v2 8 needle 128k (average) 32.0%config: 262,144 context | 25.8B (4B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| gemma-4-31B google | author-reported Author reports MRCR v2 8 needle 128k (average) 66.4%decision-model estimate p=0.98 +1 | 31.3B | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 1 | — |
| gemma-4-26B-A4B google | author-reported Author reports MRCR v2 8 needle 128k (average) 44.1%decision-model estimate p=0.98 +1 | 25.8B (4B active) | 256K | $0.00 | Single high-end GPU | Apache 2.0 | 2 | — |
| Phi-3-mini-128k-instruct microsoft | author-reported Author reports RULER 92.4decision-model estimate p=1.00 +1 | 3.82B | 128K | — | Single GPU | MIT | 0 | — |
| NVIDIA-Nemotron-Nano-9B-v2 nvidia | author-reported Author reports RULER (128K) 78.9%decision-model estimate p=0.72 +1 | 8.89B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| Kimi-Linear-48B-A3B-Instruct moonshotai | author-reported Author reports RULER (128k context length) 84.3decision-model estimate p=1.00 | 49.1B (3B active) | — | — | Multi-GPU node | MIT | 1 | — |
| gemma-4-E2B google | author-reported Author reports MRCR v2 8 needle 128k (average) 19.1%decision-model estimate p=0.99 +1 | 5.12B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| gemma-4-12B google | author-reported Author reports MRCR v2 8 needle 128k (average) 43.4%decision-model estimate p=1.00 +1 | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| gemma-4-31B-it-assistant google | author-reported Author reports MRCR v2 8 needle 128k (average) 66.4%decision-model estimate p=0.96 +1 | 470M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| DeepSeek-V4-Flash-DSpark deepseek-ai | author-reported Author reports LongBench-V2 (EM) 44.7decision-model estimate p=1.00 +1 | 165B | 1M | — | Multi-GPU node | MIT | 0 | — |
| gemma-4-26B-A4B-it-assistant google | author-reported Author reports MRCR v2 8 needle 128k (average) 44.1%decision-model estimate p=0.98 +1 | 420M (4B active) | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Nanbeige4.2-3B Nanbeige | author-reported Author reports AA-LCR 58.7config: 262,144 context | 4.17B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Kimi-K3-DSpark RadixArk | author-reported Author reports RULER V2 1M (MK/MV/QA) 4.2553decision-model estimate p=0.93 +1 | 2.25B | 1M | — | Single GPU | Not declared review | 0 | — |
| Nemotron-Cascade-2-30B-A3B nvidia | author-reported Author reports AA-LCR 39.1config: 262,144 context | 31.6B (3B active) | 256K | — | Single high-end GPU | NVIDIA Open Model License… attribution | 0 | — |
| internlm3-8b-instruct internlm | author-reported Author reports RULER(4-128K Average) 87.9 | 8.80B | 32K | — | Single GPU | Apache 2.0 | 0 | — |
| Kimi-VL-A3B-Thinking-2506 moonshotai | author-reported Author reports MMLongBench-DOC (Acc) 42.1config: 131,072 context | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| K-EXAONE-236B-A23B LGAI-EXAONE | author-reported Author reports AA-LCR 53.5Author reports OpenAI-MRCR 52.3 +1 | 237B (23B active) | 256K | — | Multi-GPU node | k-exaone review | 0 | — |
| Qwen3.8-27B Qwen | structural decision-model estimate p=0.84config: 262,144 context | 27.8B | 256K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 28.6 s · 87 tok/s |
| gpt-oss-120b openai | structural config: 131,072 context | 117B | 128K | $0.03 | Multi-GPU node | Apache 2.0 | 13 | 0.8 s · 168 tok/s |
| GLM-5.3-Flash zai-org | structural decision-model estimate p=0.72config: 1,048,576 context | 321B | 1M | $0.02 | Cluster | MIT | 9 | 8.1 s · 153 tok/s |
| gpt-oss-20b openai | structural config: 131,072 context | 20.9B | 128K | $0.02 | Single high-end GPU | Apache 2.0 | 7 | 2.8 s · 58 tok/s |
| GLM-5.3 zai-org | structural config: 1,048,576 context | 753B | 1M | $0.07 | Cluster | GLM License (glm-5.3) review | 9 | — |
| GLM-5.2 zai-org | structural decision-model estimate p=1.00config: 1,048,576 context | 753B | 1M | $0.03 | Cluster | MIT | 9 | — |
| DeepSeek-V4-Flash-0731 deepseek-ai | structural config: 1,048,576 context | 304B | 1M | $0.04 | Cluster | MIT | 7 | 15.3 s · 122 tok/s |
| Qwen3.6-35B-A3B Qwen | structural decision-model estimate p=1.00config: 262,144 context | 36.0B (3B active) | 256K | $0.05 | Multi-GPU node | Apache 2.0 | 5 | — |
| DeepSeek-R1 deepseek-ai | structural config: 163,840 context | 684B | 160K | $0.70 | Cluster | MIT | 3 | — |
| GLM-4.7-Flash zai-org | structural config: 202,752 context | 31.2B | 198K | $0.06 | Single high-end GPU | MIT | 5 | — |
| Qwen3-VL-8B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 8.77B | 256K | $0.25 | Single GPU | Apache 2.0 | 4 | — |
| Qwen2.5-7B-Instruct Qwen | structural decision-model estimate p=0.99 | 7.62B | 32K | $0.10 | Single GPU | Apache 2.0 | 3 | — |
| MiniMax-M3 MiniMaxAI | structural decision-model estimate p=1.00config: 1,048,576 context | 427B | 1M | $0.22 | Cluster | MiniMax Model License (mi… gated-threshold | 7 | — |
| Kimi-K2.6 moonshotai | structural config: 262,144 context | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 5 | — |
| gemma-3-4b-it google | structural decision-model estimate p=0.97 | 4.30B | 128K | $0.04 | Single GPU | Gemma Terms of Use attribution | 4 | — |
| Qwen3.6-27B Qwen | structural decision-model estimate p=1.00config: 262,144 context | 27.8B | 256K | $0.20 | Single high-end GPU | Apache 2.0 | 4 | — |
| Kimi-K2.5 moonshotai | structural config: 262,144 context | 1.03T | 256K | $0.45 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| Qwen2.5-Coder-32B-Instruct Qwen | structural decision-model estimate p=1.00 | 32.8B | 32K | $0.06 | Single high-end GPU | Apache 2.0 | 4 | — |
| GLM-5 zai-org | structural config: 202,752 context | 754B | 198K | $0.60 | Cluster | MIT | 5 | — |
| gemma-3-27b-it google | structural decision-model estimate p=0.98 | 27.4B | 128K | $0.08 | Single high-end GPU | Gemma Terms of Use attribution | 4 | — |
| Qwen3.8-Flash-Next Qwen | structural decision-model estimate p=0.83config: 262,144 context | 180B | 256K | $0.15 | Multi-GPU node | Qwen License (qwen-commun… gated-threshold | 2 | — |
| DeepSeek-R1-0528 deepseek-ai | structural config: 163,840 context | 685B | 160K | $0.50 | Cluster | MIT | 4 | — |
| MiniMax-M2.5 MiniMaxAI | structural config: 196,608 context | 229B | 192K | $0.27 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 4 | — |
| Qwen3-Coder-30B-A3B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 30.5B (3B active) | 256K | $0.07 | Single high-end GPU | Apache 2.0 | 3 | — |
| Qwen3-VL-30B-A3B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 31.1B (3B active) | 256K | $0.15 | Single high-end GPU | Apache 2.0 | 4 | — |
| DeepSeek-V3 deepseek-ai | structural config: 163,840 context | 684B | 160K | $0.26 | Cluster | Not declared review | 2 | — |
| Qwen3-Next-80B-A3B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 81.3B (3B active) | 256K | $0.07 | Multi-GPU node | Apache 2.0 | 4 | — |
| gemma-4-E4B-it google | structural decision-model estimate p=0.99config: 131,072 context | 8.00B | 128K | — | Single GPU | Apache 2.0 | 1 | — |
| GLM-5.1 zai-org | structural config: 202,752 context | 754B | 198K | $0.96 | Cluster | MIT | 4 | — |
| Kimi-K2-Instruct moonshotai | structural config: 131,072 context | 1.03T | 128K | $0.57 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| DeepSeek-V3-0324 deepseek-ai | structural config: 163,840 context | 685B | 160K | $0.24 | Cluster | MIT | 3 | — |
| GLM-4.5-Air zai-org | structural config: 131,072 context | 110B | 128K | $0.13 | Multi-GPU node | MIT | 4 | — |
| MiniMax-M2.7 MiniMaxAI | structural config: 204,800 context | 229B | 200K | $0.21 | Multi-GPU node | other review | 4 | — |
| gemma-3-12b-it google | structural decision-model estimate p=0.98 | 12.2B | 128K | $0.04 | Single high-end GPU | Gemma Terms of Use attribution | 3 | — |
| DeepSeek-V3.2 deepseek-ai | structural config: 163,840 context | 685B | 160K | $0.21 | Cluster | MIT | 2 | — |
| Qwen2.5-Coder-7B-Instruct Qwen | structural decision-model estimate p=1.00 | 7.62B | 32K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| DeepSeek-V4-Pro-0813 deepseek-ai | structural config: 1,048,576 context | 1.65T | 1M | $0.12 | Cluster | MIT | 6 | — |
| Qwen3-4B-Instruct-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Coder-Next Qwen | structural decision-model estimate p=1.00config: 262,144 context | 79.7B | 256K | $0.12 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3-VL-4B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-VL-2B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-235B-A22B-Instruct-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 235B (22B active) | 256K | $0.09 | Multi-GPU node | Apache 2.0 | 5 | — |
| Qwen2.5-72B-Instruct Qwen | structural decision-model estimate p=0.99 | 72.7B | 32K | $0.36 | Multi-GPU node | Qwen License (qwen) gated-threshold | 3 | — |
| GLM-4.7 zai-org | structural config: 202,752 context | 358B | 198K | $0.32 | Cluster | MIT | 4 | — |
| Qwen3-30B-A3B-Instruct-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 30.5B (3B active) | 256K | $0.09 | Single high-end GPU | Apache 2.0 | 2 | — |
| DeepSeek-R1-Distill-Qwen-32B deepseek-ai | structural config: 131,072 context | 32.8B | 128K | — | Single high-end GPU | MIT | 2 | — |
| DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai | structural config: 131,072 context | 1.78B | 128K | — | Single GPU | MIT | 1 | — |
| GLM-4.6 zai-org | structural decision-model estimate p=1.00config: 202,752 context | 357B | 198K | $0.40 | Cluster | MIT | 5 | — |
| DeepSeek-R1-Distill-Qwen-7B deepseek-ai | structural config: 131,072 context | 7.62B | 128K | $0.15 | Single GPU | MIT | 2 | — |
| Qwen2-7B-Instruct Qwen | structural decision-model estimate p=0.99 | 7.62B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen3.5-2B Qwen | structural decision-model estimate p=1.00config: 262,144 context | 2.27B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| MiniMax-M2 MiniMaxAI | structural config: 196,608 context | 229B | 192K | $0.26 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-4B-Thinking-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 4.02B | 256K | $0.01 | Single GPU | Apache 2.0 | 2 | — |
| Qwen3-VL-235B-A22B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 236B (22B active) | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3.5-0.8B Qwen | structural decision-model estimate p=0.99config: 262,144 context | 873M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Kimi-K2.7-Code moonshotai | structural decision-model estimate p=1.00config: 262,144 context | 1.03T | 256K | $0.67 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 4 | — |
| DeepSeek-R1-Distill-Qwen-14B deepseek-ai | structural config: 131,072 context | 14.8B | 128K | $0.20 | Single high-end GPU | MIT | 2 | — |
| Step-3.5-Flash stepfun-ai | structural decision-model estimate p=1.00config: 262,144 context | 199B | 256K | $0.10 | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-R1-Distill-Llama-8B deepseek-ai | structural config: 131,072 context | 8.03B | 128K | $0.05 | Single GPU | MIT | 2 | — |
| Qwen3.8-2.4T-A95B Qwen | structural decision-model estimate p=0.88config: 262,144 context | 2.45T (95B active) | 256K | $2.00 | Cluster | Qwen License (qwen3.8-max) gated-threshold | 5 | — |
| Qwen3-VL-Embedding-2B Qwen | structural config: 262,144 context | 2.13B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen3-Coder-480B-A35B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 480B (35B active) | 256K | $0.22 | Cluster | Apache 2.0 | 3 | — |
| DeepSeek-R1-Distill-Llama-70B deepseek-ai | structural config: 131,072 context | 70.6B | 128K | — | Multi-GPU node | MIT | 2 | — |
| Qwen2.5-14B-Instruct Qwen | structural decision-model estimate p=0.98 | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Kimi-K2-Thinking moonshotai | structural decision-model estimate p=1.00config: 262,144 context | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| Qwen2.5-32B-Instruct Qwen | structural decision-model estimate p=0.99 | 32.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| DeepSeek-R1-0528-Qwen3-8B deepseek-ai | structural config: 131,072 context | 8.19B | 128K | — | Single GPU | MIT | 1 | — |
| QwQ-32B Qwen | structural decision-model estimate p=0.96 | 32.8B | 40K | — | Single high-end GPU | Apache 2.0 | 2 | — |
| DeepSeek-V4-Flash-Vision-Exp deepseek-ai | structural config: 1,048,576 context | 305B | 1M | $0.22 | Cluster | MIT | 2 | — |
| Qwen2.5-Coder-14B-Instruct Qwen | structural decision-model estimate p=0.99 | 14.8B | 32K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| Qwen3-VL-32B-Instruct Qwen | structural decision-model estimate p=1.00config: 262,144 context | 33.4B | 256K | — | Multi-GPU node | Apache 2.0 | 2 | — |
| Qwen2.5-Coder-7B Qwen | structural decision-model estimate p=0.93 | 7.62B | 32K | — | Single GPU | Apache 2.0 | 2 | — |
| Hy3 tencent | structural decision-model estimate p=1.00config: 262,144 context | 299B | 256K | $0.08 | Cluster | Apache 2.0 | 3 | — |
| GLM-4.5 zai-org | structural config: 131,072 context | 358B | 128K | $0.60 | Cluster | MIT | 2 | — |
| Qwen3-VL-Embedding-8B Qwen | structural config: 262,144 context | 8.14B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2.5-7B Qwen | structural decision-model estimate p=0.99config: 131,072 context | 7.62B | 128K | $0.10 | Single GPU | Apache 2.0 | 1 | — |
| Kimi-K2-Instruct-0905 moonshotai | structural decision-model estimate p=1.00config: 262,144 context | 1.03T | 256K | $0.60 | Cluster | Kimi (Modified MIT) (modi… gated-threshold | 3 | — |
| MiniMax-M2.1 MiniMaxAI | structural config: 196,608 context | 229B | 192K | $0.30 | Multi-GPU node | MiniMax (Modified MIT) (m… review | 3 | — |
| Qwen3-VL-235B-A22B-Thinking Qwen | structural decision-model estimate p=1.00config: 262,144 context | 236B (22B active) | 256K | — | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-Coder-V2-Lite-Instruct deepseek-ai | structural config: 163,840 context | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen2.5-1.5B Qwen | structural config: 131,072 context | 1.54B | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Phi-3.5-mini-instruct microsoft | structural decision-model estimate p=0.99config: 131,072 context | 3.82B | 128K | — | Single GPU | MIT | 0 | — |
| HunyuanOCR tencent | structural config: 131,072 context | 1.12B | 128K | — | Laptop / edge | tencent-hunyuan-community review | 0 | — |
| Phi-3.5-vision-instruct microsoft | structural decision-model estimate p=0.97config: 131,072 context | 4.15B | 128K | — | Single GPU | MIT | 0 | — |
| Phi-4-mini-instruct microsoft | structural decision-model estimate p=0.98config: 131,072 context | 3.84B | 128K | — | Single GPU | MIT | 0 | — |
| gemma-4-E4B google | structural decision-model estimate p=1.00config: 131,072 context | 8.00B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3-VL-8B-Thinking Qwen | structural decision-model estimate p=1.00config: 262,144 context | 8.77B | 256K | — | Single GPU | Apache 2.0 | 3 | — |
| Hermes-3-Llama-3.1-8B NousResearch | structural config: 131,072 context | 8.03B | 128K | — | Single GPU | Llama 3 Community License attribution | 1 | — |
| SmolLM3-3B HuggingFaceTB | structural decision-model estimate p=0.94 | 3.08B | 64K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen2.5-7B-Instruct-1M Qwen | structural decision-model estimate p=1.00name: 1M +1 | 7.62B | 986K | — | Single GPU | Apache 2.0 | 1 | — |
| Qwen2-72B-Instruct Qwen | structural decision-model estimate p=1.00 | 72.7B | 32K | — | Multi-GPU node | tongyi-qianwen review | 2 | — |
| GLM-4.6V-Flash zai-org | structural decision-model estimate p=0.74config: 131,072 context | 10.3B | 128K | $0.30 | Single high-end GPU | MIT | 2 | — |
| DeepSeek-V3.2-Exp deepseek-ai | structural config: 163,840 context | 685B | 160K | $0.27 | Cluster | MIT | 2 | — |
| Qwen3-235B-A22B-Thinking-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 235B (22B active) | 256K | $0.23 | Multi-GPU node | Apache 2.0 | 3 | — |
| Qwen3-30B-A3B-Thinking-2507 Qwen | structural decision-model estimate p=1.00config: 262,144 context | 30.5B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| LFM2.5-2.6B LiquidAI | structural decision-model estimate p=0.99config: 131,072 context | 2.70B | 128K | $0.00 | Single GPU | lfm1.0 review | 1 | — |
| Qwen2-0.5B Qwen | structural config: 131,072 context | 494M | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Llama-3.1-Nemotron-70B-Instruct-HF nvidia | structural config: 131,072 context | 70.6B | 128K | — | Multi-GPU node | Llama 3.1 Community Licen… attribution | 1 | — |
| Qwen3-Next-80B-A3B-Thinking Qwen | structural config: 262,144 context | 81.3B (3B active) | 256K | $0.15 | Multi-GPU node | Apache 2.0 | 1 | — |
| MiMo-V2.6-Pro-RL XiaomiMiMo | structural decision-model estimate p=1.00tag: long-context +1 | 1.02T | 1M | $0.39 | Cluster | MIT | 2 | — |
| chandra-ocr-2 datalab-to | structural config: 262,144 context | 5.30B | 256K | — | Single GPU | OpenRAIL attribution | 0 | — |
| Qwen2.5-14B Qwen | structural decision-model estimate p=0.99config: 131,072 context | 14.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| MiniCPM5-2B openbmb | structural tag: long-contextconfig: 131,072 context | 2.52B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| MiMo-V2.6-Flash-RL XiaomiMiMo | structural decision-model estimate p=1.00tag: long-context +1 | 311B | 1M | $0.09 | Cluster | MIT | 2 | — |
| Hy4-preview tencent | structural config: 1,048,576 context | 780B | 1M | $0.75 | Cluster | Apache 2.0 | 3 | — |
| Laguna-S-2.1 poolside | structural decision-model estimate p=1.00config: 1,048,576 context | 118B | 1M | $0.00 | Multi-GPU node | — review | 2 | — |
| Qwen3-VL-4B-Thinking Qwen | structural decision-model estimate p=1.00config: 262,144 context | 4.44B | 256K | — | Single GPU | Apache 2.0 | 2 | — |
| Qwen2.5-32B Qwen | structural decision-model estimate p=0.99config: 131,072 context | 32.8B | 128K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| surya-ocr-2 datalab-to | structural config: 262,144 context | 686M | 256K | — | Laptop / edge | OpenRAIL attribution | 1 | — |
| Step-3.7-Flash stepfun-ai | structural decision-model estimate p=1.00config: 262,144 context | 201B | 256K | $0.20 | Multi-GPU node | Apache 2.0 | 3 | — |
| DeepSeek-V2-Lite deepseek-ai | structural config: 163,840 context | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| gemma-3-4b-pt google | structural decision-model estimate p=0.97 | 4.30B | — | — | Single GPU | Gemma Terms of Use attribution | 1 | — |
| translategemma-4b-it google | structural config: 131,072 context | 4.30B | 128K | — | Single GPU | Gemma Terms of Use attribution | 0 | — |
| Ornith-1.0-9B ornith-ai | structural config: 262,144 context | 1.47M | 256K | — | Laptop / edge | MIT | 1 | — |
| Qwen3-VL-30B-A3B-Thinking Qwen | structural decision-model estimate p=1.00config: 262,144 context | 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=0.99config: 131,072 context | 108B | 128K | $0.30 | Multi-GPU node | MIT | 3 | — |
| gpt-oss-safeguard-20b openai | structural config: 131,072 context | 21.5B | 128K | $0.07 | Single high-end GPU | Apache 2.0 | 2 | — |
| Phi-3.5-MoE-instruct microsoft | structural decision-model estimate p=1.00config: 131,072 context | 41.9B | 128K | — | Multi-GPU node | MIT | 0 | — |
| MiMo-V2.5 XiaomiMiMo | structural tag: long-contextconfig: 1,048,576 context | 311B | 1M | $0.12 | Cluster | MIT | 2 | — |
| Kimi-VL-A3B-Instruct moonshotai | structural decision-model estimate p=1.00tag: long-context +1 | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| LFM2.5-8B-A1B LiquidAI | structural decision-model estimate p=0.99 | 8.47B (1B active) | 125K | — | Single GPU | lfm1.0 review | 0 | — |
| MiMo-V2.5-Pro XiaomiMiMo | structural decision-model estimate p=1.00tag: long-context +1 | 1.02T | 1M | $0.30 | Cluster | MIT | 2 | — |
| Qwen2-7B Qwen | structural config: 131,072 context | 7.62B | 128K | — | Single GPU | Apache 2.0 | 1 | — |
| MiniCPM5-1B openbmb | structural tag: long-contextconfig: 131,072 context | 1.08B | 128K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Phi-3-vision-128k-instruct microsoft | structural decision-model estimate p=1.00name: 128k +1 | 4.15B | 128K | — | Single GPU | MIT | 0 | — |
| Ling-3.0-flash inclusionAI | structural decision-model estimate p=0.98config: 262,144 context | 127B | 256K | $0.02 | Multi-GPU node | MIT | 3 | — |
| DeepSeek-V2-Lite-Chat deepseek-ai | structural config: 163,840 context | 15.7B | 160K | — | Single high-end GPU | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled Jackrong | structural config: 262,144 context | 27.8B | 256K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| dots.ocr dots-studio | structural config: 131,072 context | 3.04B | 128K | — | Single GPU | MIT | 0 | — |
| Qwen3.5-0.8B-Base Qwen | structural config: 262,144 context | 873M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| MiniCPM-V-4.6 openbmb | structural config: 262,144 context | 1.30B | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Ornith-1.0-35B ornith-ai | structural config: 262,144 context | 665K | 256K | — | Laptop / edge | MIT | 0 | — |
| granite-4.1-8b ibm-granite | structural config: 131,072 context | 8.79B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| OvisOCR2 ATH-MaaS | structural config: 262,144 context | 853M | 256K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2-1.5B Qwen | structural config: 131,072 context | 1.54B | 128K | — | Laptop / edge | Apache 2.0 | 1 | — |
| Qwen2.5-14B-Instruct-1M Qwen | structural decision-model estimate p=1.00name: 1M +1 | 14.8B | 986K | — | Single high-end GPU | Apache 2.0 | 1 | — |
| granite-4.1-3b ibm-granite | structural config: 131,072 context | 3.40B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3.5-4B-Base Qwen | structural config: 262,144 context | 4.66B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Hunyuan-A13B-Instruct tencent | structural decision-model estimate p=1.00 | 80.4B (13B active) | 32K | $0.14 | Multi-GPU node | tencent-hunyuan-a13b review | 1 | — |
| Llama-3.2-1B-Instruct unsloth | structural config: 131,072 context | 1.24B | 128K | — | Laptop / edge | Llama 3.2 Community Licen… attribution | 0 | — |
| DeepSeek-V3.1-Base deepseek-ai | structural config: 163,840 context | 685B | 160K | — | Cluster | MIT | 0 | — |
| Phi-4-mini-reasoning microsoft | structural config: 131,072 context | 3.84B | 128K | — | Single GPU | MIT | 1 | — |
| DeepSeek-Coder-V2-Instruct deepseek-ai | structural config: 163,840 context | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| gemma-3-12b-pt google | structural decision-model estimate p=0.98 | 12.2B | — | — | Single high-end GPU | Gemma Terms of Use attribution | 1 | — |
| Qwen3.5-9B-Base Qwen | structural config: 262,144 context | 9.65B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Meta-Llama-3.1-8B-Instruct unsloth | structural config: 131,072 context | 8.03B | 128K | — | Single GPU | Llama 3.1 Community Licen… attribution | 1 | — |
| Jamba-v0.1 ai21labs | structural decision-model estimate p=1.00config: 262,144 context | 51.6B | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| Llama-3_3-Nemotron-Super-49B-v1_5 nvidia | structural decision-model estimate p=1.00config: 131,072 context | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| Qwen-AgentWorld-35B-A3B Qwen | structural config: 262,144 context | 34.7B (3B active) | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| Qwen3.5-2B-Base Qwen | structural config: 262,144 context | 2.27B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| DeepSeek-V2-Chat deepseek-ai | structural config: 163,840 context | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| DeepSeek-R1-Zero deepseek-ai | structural config: 163,840 context | 684B | 160K | — | Cluster | MIT | 0 | — |
| ReaderLM-v2 jinaai | structural decision-model estimate p=1.00config: 512,768 context | 1.54B | 501K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 1 | — |
| Llama-3.1-Nemotron-Nano-8B-v1 nvidia | structural decision-model estimate p=0.99config: 131,072 context | 8.03B | 128K | — | Single GPU | NVIDIA Open Model License… attribution | 1 | — |
| Meta-Llama-3.1-8B-Instruct NousResearch | structural decision-model estimate p=0.99config: 131,072 context | 8.03B | 128K | — | Single GPU | Llama 3.1 Community Licen… attribution | 1 | — |
| Llama-xLAM-2-8b-fc-r Salesforce | structural config: 131,072 context | 8.03B | 128K | — | Single GPU | CC BY-NC 4.0 non-commercial | 1 | — |
| Idefics3-8B-Llama3 HuggingFaceM4 | structural config: 131,072 context | 8.46B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| t5gemma-2-270m-270m google | structural decision-model estimate p=0.98 | 786M | — | — | Laptop / edge | Gemma Terms of Use attribution | 0 | — |
| MiMo-V2-Flash XiaomiMiMo | structural decision-model estimate p=1.00config: 262,144 context | 310B | 256K | — | Cluster | MIT | 0 | — |
| granite-4.2-8b ibm-granite | structural decision-model estimate p=1.00config: 131,072 context | 8.79B | 128K | $0.06 | Single GPU | Apache 2.0 | 2 | — |
| Ornith-1.5-9B ornith-ai | structural config: 262,144 context | 9.65B | 256K | — | Single GPU | MIT | 1 | — |
| Mage-VL microsoft | structural config: 262,144 context | 4.74B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| ERNIE-4.5-21B-A3B-Thinking baidu | structural decision-model estimate p=0.98config: 131,072 context | 21.8B (3B active) | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| DeepSeek-V2.5 deepseek-ai | structural config: 163,840 context | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| Qwen2-72B Qwen | structural config: 131,072 context | 72.7B | 128K | — | Multi-GPU node | tongyi-qianwen review | 1 | — |
| Llama-3_3-Nemotron-Super-49B-v1 nvidia | structural decision-model estimate p=1.00config: 131,072 context | 49.9B | 128K | — | Multi-GPU node | NVIDIA Open Model License… attribution | 0 | — |
| Kimi-VL-A3B-Thinking moonshotai | structural decision-model estimate p=1.00config: 131,072 context | 16.4B (3B active) | 128K | — | Single high-end GPU | MIT | 0 | — |
| Hermes-3-Llama-3.1-405B NousResearch | structural config: 131,072 context | 406B | 128K | $1.00 | Cluster | Llama 3 Community License attribution | 2 | — |
| North-Mini-Code-1.0 CohereLabs | structural decision-model estimate p=0.98config: 500,000 context | 30.5B | 488K | $0.00 | Single high-end GPU | Apache 2.0 | 1 | — |
| granite-4.0-h-tiny ibm-granite | structural config: 131,072 context | 6.94B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| Qwen3-VL-2B-Thinking Qwen | structural decision-model estimate p=1.00config: 262,144 context | 2.13B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| MiniMax-Text-01 MiniMaxAI | structural config: 10,240,000 context | 456B | 9.8M | $0.20 | Cluster | Not declared review | 1 | — |
| Ornith-1.5-35B-A3B ornith-ai | structural config: 262,144 context | 36.0B (3B active) | 256K | — | Multi-GPU node | MIT | 0 | — |
| translategemma-12b-it google | structural config: 131,072 context | 12.2B | 128K | — | Single high-end GPU | Gemma Terms of Use attribution | 0 | — |
| MiniMax-M1-80k MiniMaxAI | structural config: 10,240,000 context | 456B | 9.8M | $0.55 | Cluster | Apache 2.0 | 1 | — |
| Nanbeige4.1-3B Nanbeige | structural config: 262,144 context | 3.93B | 256K | — | Single GPU | Apache 2.0 | 1 | — |
| Solar-Open-100B upstage | structural decision-model estimate p=1.00config: 131,072 context | 103B | 128K | — | Multi-GPU node | upstage-solar-license review | 0 | — |
| Hermes-3-Llama-3.1-70B NousResearch | structural config: 131,072 context | 70.6B | 128K | $0.70 | Multi-GPU node | Llama 3 Community License attribution | 3 | — |
| EXAONE-4.5-33B LGAI-EXAONE | structural decision-model estimate p=1.00config: 262,144 context | 34.4B | 256K | — | Multi-GPU node | exaone review | 0 | — |
| Hy3-preview tencent | structural decision-model estimate p=1.00config: 262,144 context | 299B | 256K | $0.18 | Cluster | Other review | 1 | — |
| granite-4.0-h-small ibm-granite | structural config: 131,072 context | 32.2B | 128K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| DeepSeek-V2 deepseek-ai | structural config: 163,840 context | 236B | 160K | — | Multi-GPU node | DeepSeek License (deepsee… attribution | 0 | — |
| granite-3.3-8b-instruct ibm-granite | structural decision-model estimate p=0.98config: 131,072 context | 8.17B | 128K | — | Single GPU | Apache 2.0 | 0 | — |
| PaddleOCR-VL-1.6 PaddlePaddle | structural config: 131,072 context | 959M | 128K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Intern-Decision-4B internlm | structural config: 262,144 context | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-0.8B internlm | structural config: 262,144 context | 853M | 256K | — | Laptop / edge | Apache 2.0 | 0 | — |
| Winnow-12B EldanRing | structural config: 262,144 context | — | 256K | — | — | Apache 2.0 | 0 | — |
| JevK5 alibiserikbay | structural config: 262,144 context | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Intern-Decision-2B internlm | structural config: 262,144 context | 2.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| Tev1-4B-experimental togethercomputer | structural config: 262,144 context | 4.66B | 256K | $0.04 | Single GPU | Not declared review | 1 | — |
| Tev1-0.8B-experimental togethercomputer | structural config: 262,144 context | 873M | 256K | — | Laptop / edge | Not declared review | 0 | — |
| xor juspay | structural config: 262,144 context | 35.1B | 256K | — | Multi-GPU node | Apache 2.0 | 0 | — |
| openjev openjev | structural config: 262,144 context | 27.4B | 256K | — | Single high-end GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| Jev-Omni akhilaaa3 | structural config: 262,144 context | 12.0B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| JEV-27B autotrust | structural decision-model estimate p=0.85config: 262,144 context | 26.9B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| pplx-decider-v1-27b perplexity-ai | structural config: 262,144 context | 26.1B | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| decider-2b Mapika | structural config: 262,144 context | 1.88B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| decider-4b Mapika | structural config: 262,144 context | 4.21B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| jpt-4b kirp | structural config: 262,144 context | 4.54B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| LFM2.5-2.6B-RLCD monotykamary | structural config: 131,072 context | 2.70B | 128K | — | Single GPU | lfm1.0 review | 0 | — |
| this-that-model-1.0 flock-io | structural config: 262,144 context | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| decider-35b-a3b-nvfp4 Mapika | structural config: 262,144 context | 17.9B (3B active) | 256K | — | Single high-end GPU | Apache 2.0 | 0 | — |
| metask-jev-4b-policy-mix wayfind | structural config: 262,144 context | 4.54B | 256K | — | Single GPU | Apache 2.0 | 0 | — |
| this-that-model-1.2 flock-io | structural config: 262,144 context | 1.88B | 256K | — | Single GPU | MIT | 0 | — |
| Eikos-27B-FP8 caiovicentino1 | structural config: 262,144 context | 27.8B | 256K | — | Single high-end GPU | MIT | 0 | — |
| blink-27b thegovind | structural config: 262,144 context | 26.9B | 256K | — | Single high-end GPU | Research / non-commercial… non-commercial | 0 | — |
| jpt-0.8b kirp | structural config: 262,144 context | 853M | 256K | — | Laptop / edge | CC BY-NC 4.0 non-commercial | 0 | — |
| jpt-9b kirp | structural config: 262,144 context | 9.41B | 256K | — | Single GPU | CC BY-NC 4.0 non-commercial | 0 | — |
| jebadiah-27b frontier-infra | structural config: 262,144 context | 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 "Read long documents"
- /feeds/for/long-context.xml(RSS 2.0) · one item per model with measured or author-reported evidence for this job
- /feeds/for/long-context.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.