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
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
| # | Model | Score |
|---|---|---|
| 151 | GPT OSS 120B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 62.4% |
| 152 | GPT OSS 120Bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.4% |
| 153 | Devstral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.6% |
| 154 | Ling 2.6 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.2% |
| 155 | GPT OSS 20b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 60.7% |
| 156 | GPT OSS 20bofficial model card Table 3 · reasoning high · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.7% |
| 157 | Nemotron 3 Super 120B A12Bofficial blog Figure 3 · rounded · harness not labeled· Reported by NVIDIA Developer· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.5% |
| 158 | Nemotron 3 Super 120B A12B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 3 sources
| 60.5% |
| 159 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · OpenCode · report Table 8 BF16· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.5% |
| 160 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · OpenHands· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.5% |
| 161 | Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60.4% |
| 162 | LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 60.4% |
| 163 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · OpenCode v1.17.8 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60% |
| 164 | GLM 4.7 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 59.2% |
| 165 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · OpenCode· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.2% |
| 166 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Copilot v1.0.71 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 58.4% |
| 167 | GLM 4.5 Air· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 57.6% |
| 168 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Claude v2.1.126 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.4% |
| 169 | Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57% |
| 170 | MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 56% |
| 171 | MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 55.6% |
| 172 | GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.6% |
| 173 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Pi v0.80.10 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.5% |
| 174 | longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.4% |
| 175 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · Codex· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.7% |
| 176 | Devstral Small 2505· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.6% |
| 177 | Nova 2 LiteAmazon Nova 2 technical report · standard inference, v1· Reported by Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.6% |
| 178 | GPT OSS 20bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.2% |
| 179 | Nemotron 3.5 Lightning 30B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 52.8% |
| 180 | GPT OSS 120Bofficial model card Table 3 · reasoning medium · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.6% |
| 181 | Nemotron 3.5 Lightning 30B A3BNeMo Evaluator release-table setting· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.6% |
| 182 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Mini-SWE-Agent v2.4.5 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.7% |
| 183 | o3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.3% |
| 184 | Claude 3.5 Sonnet· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49% |
| 185 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · OpenHands v1.36.1 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 48.7% |
| 186 | GPT OSS 120Bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47.9% |
| 187 | Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 47.7% |
| 188 | MiniCPM5-2B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.4% |
| 189 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Hermes v0.18.2 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.7% |
| 190 | Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 45% |
| 191 | DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 44.6% |
| 192 | DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42% |
| 193 | O1 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.3% |
| 194 | o1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41% |
| 195 | Claude Haiku 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.6% |
| 196 | Nemotron 3 Nano 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.8% |
| 197 | GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38% |
| 198 | GPT OSS 20bofficial model card Table 3 · reasoning low · published setting; Table 3 does not further specify tool access · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.4% |
| 199 | Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34% |
| 200 | GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 33.2% |
Showing 151–200 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)