Skip to content

Benchmark

SWE-bench Verified

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
130
Scores recorded
205
Sources
5
IQ weight
2.70

Score distribution

70%
Mean
73.5%
Median
13.7%
Std dev
51.6%
10th percentile
80.8%
90th percentile
8.7%
Min
8.7%96%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.70 for chat models, measured over 129 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51MiMo V2.5 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78.9%
52MiMo V2.5 ProXiaomi MiMo-V2.5-Pro official launch table · published coding-agent setting· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.9%
53Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78.8%
54Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · internal bash + file-edit scaffold · 200K · temp 1.0 · top_p .95· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.8%
55DeepSeek V4 FlashDeepSeek V4 official model card · Think High· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.6%
56Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78%
57Gemini 3 Flashsingle attempt · internal bash/file/submit scaffold · mean of 5 runs· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78%
58Hy3 (Deep Infra)· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78%
59Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78%
60MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78%
61MiMo V2 ProXiaomi MiMo-V2-Pro release table · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78%
62GLM 5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 4 sources
77.8%
63GLM 5GLM-5 official release table· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.8%
64Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.7%
65Qwen3.7 PlusQwen3.7-Plus release · internal bash + file-edit agent scaffold · temp 1.0 · top_p 0.95 · 200K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.7%
66Inkling FP4· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
77.6%
67Mistral Medium 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.6%
68Mistral Medium 3.5 128b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim77.6%
69Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.4%
70Claude Sonnet 4.5Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.2%
71Claude Sonnet 4.5standard evaluation· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.2%
72Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
77.2%
73Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · internal bash + file-edit scaffold · 200K· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.2%
74Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.8%
75Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 4 sources
76.8%
76Doubao Seed 2.0 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.5%
77Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
76.4%
78Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.4%
79GPT 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.3%
80GPT-5.1-Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.3%
81Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.2%
82Gemini 3 Pro PreviewGemini 3 Pro Model Card · results as of November 2025 · single attempt· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.2%
83Gemini 3 Pro PreviewOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.2%
84MiniMax M2.5official prose · OpenCode · default prompt· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.1%
85Muse Glimmer 30B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
76%
86Muse Glimmer 30Bhigh reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76%
87GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.9%
88MiMo V2 Omni· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.8%
89MiMo V2 OmniXiaomi MiMo-V2-Omni release table · code-and-text agent table · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.8%
90Laguna M.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim74.6%
91Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.5%
92GPT-5 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.5%
93Step 3.5 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
74.4%
94Step 3.5 FlashStep 3.5 Flash official headline table · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74.4%
95MiniMax M2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
74%
96Ring 2.6 1T· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim74%
97GLM 4.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
73.8%
98DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.7%
99GPT-5.1 Codex· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
100Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.5%

Showing 51–100 of 205 results.

Data credits: Data by LLM Stats · Hugging Face official benchmark leaderboards; licence varies by benchmark · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Steel.dev Agent Leaderboards, MIT (licence) · OpenEvals/leaderboard-data, MIT (licence)