Benchmark
SWE-bench Multilingual
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 65
- Scores recorded
- 103
- Sources
- 3
- IQ weight
- 2.97
Score distribution
- 71.9%
- Mean
- 73.8%
- Median
- 13.1%
- Std dev
- 54.5%
- 10th percentile
- 86.6%
- 90th percentile
- 30.5%
- Min
This benchmark has a weight of 2.97 for chat models, measured over 58 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 |
|---|---|---|
| 51 | Qwen3.7 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. | 75.8% |
| 52 | MiniMax M2.5main capability figure· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.1% |
| 53 | Qwen 3.8 27Bmini-SWE-agent · temp 1.0 · top_p 0.95 · 256K· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.8% |
| 54 | Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.8% |
| 55 | Qwen3.6 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. | 73.8% |
| 56 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.7% |
| 57 | DeepSeek V4 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 73.3% |
| 58 | DeepSeek V4 FlashDeepSeek V4 official model card · Think Max· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.3% |
| 59 | GLM 5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 73.3% |
| 60 | GLM 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. | 73.3% |
| 61 | Kimi 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. | 73% |
| 62 | Kimi K2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 73% |
| 63 | MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.5% |
| 64 | Ling 3.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 72.4% |
| 65 | MiMo V2 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 71.7% |
| 66 | MiMo V2 FlashMiMo-V2-Flash final evaluation · published code-agent setting · harness unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.7% |
| 67 | MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.7% |
| 68 | MiMo 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. | 71.7% |
| 69 | Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 71.3% |
| 70 | Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · internal scaffold · 200K· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.3% |
| 71 | DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.2% |
| 72 | DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.2% |
| 73 | DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · resolved· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.2% |
| 74 | DeepSeek 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. | 70.2% |
| 75 | DeepSeek 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. | 69.7% |
| 76 | Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 69.3% |
| 77 | Qwen3.5 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. | 69.3% |
| 78 | DeepSeek V3.2Non-thinking mode · temperature 1.0 · 128K context · resolved· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.9% |
| 79 | NVIDIA Nemotron 3.5 Super VL 120B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 67.7% |
| 80 | Nemotron 3 Ultra· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 67.7% |
| 81 | Nemotron 3 UltraNeMo Evaluator SDK · official table· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.7% |
| 82 | Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 67.2% |
| 83 | Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.2% |
| 84 | GLM 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.7% |
| 85 | Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.7% |
| 86 | Qwen3 Coder Next· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 64.3% |
| 87 | Laguna XS 2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 63.1% |
| 88 | Devstral 2 123b Instruct 2512official model card· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.3% |
| 89 | Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.1% |
| 90 | DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.9% |
| 91 | Laguna XS.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.7% |
| 92 | MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 56.5% |
| 93 | Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.7% |
| 94 | DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.5% |
| 95 | Kimi K2 Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 47.3% |
| 96 | 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 2 sources
| 45.8% |
| 97 | 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. | 45.8% |
| 98 | Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.9% |
| 99 | 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
| 39.3% |
| 100 | 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. | 39.3% |
Showing 51–100 of 103 results.
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats · 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.