Skip to content

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
30.5%96.6%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
1Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.6%
2Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.9%
3Claude Opus 5.5Opus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.9%
4Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.3%
5Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.3%
6Claude Opus 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.5%
7Claude Opus 5Opus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.5%
8Claude Opus 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.5%
9Claude Fable 5.1Opus 5.5 System Card capability section· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.1%
10Claude Fable 5.1System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.1%
11Ling 3.1 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim88.5%
12Claude Fable 5Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.6%
13Claude Fable 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.6%
14Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.4%
15Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.4%
16Claude Opus 4.8Opus 5 System Card capability summary · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.84.4%
17Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.7%
18Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.7%
19Hy4 preview· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
82.9%
20Hy4 previewHF Eval Result / Resolved· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.9%
21Inkling 2 Small· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim81.2%
22Qwen 3.8 Flash Next· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
81%
23Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · mini-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.81%
24Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81%
25Qwen3.8 Flashmini-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.81%
26Claude Opus 4.7adaptive thinking · max effort · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.5%
27Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.5%
28Qwen3.8 Omni Flashmini-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.80.5%
29Laguna S 2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.5%
30Beam 1.0 501B A23B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
78.3%
31Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%
32Claude Sonnet 5adaptive thinking · max effort · 5 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.3%
33Qwen3.7 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%
34Qwen3.7 MaxQwen3.7-Max 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.78.3%
35Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.8%
36Claude Opus 4.6Anthropic Opus 4.6 launch page · adaptive thinking · max effort unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.8%
37Claude Opus 4.6mini-SWE-agent · temp 1.0 · top_p 0.95 · 256K · max effort· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.5%
38LongCat 2.0· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim77.3%
39Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
76.7%
40Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · in-house SWE-agent-derived harness · avg@10· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.7%
41MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
76.5%
42MiniMax M2.7MiniMax M2.7 official release prose· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.5%
43Claude Opus 4.564K thinking budget · 200K context · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.2%
44Claude Opus 4.5no extended thinking · 200K context · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.76.2%
45DeepSeek V4 Pro· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim76.2%
46Claude Sonnet 4.6adaptive thinking · max effort · 10 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.75.9%
47Hy3 (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
75.8%
48Hy3 (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.75.8%
49Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.8%
50Qwen3.7 Plusmini-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.75.8%

Showing 1–50 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.