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
51Qwen3.7 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%
52MiniMax 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%
53Qwen 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%
54Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.8%
55Qwen3.6 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%
56Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
57DeepSeek V4 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
73.3%
58DeepSeek 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%
59GLM 5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
60GLM 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%
61Kimi 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%
62Kimi K2.5· 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%
63MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.5%
64Ling 3.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
72.4%
65MiMo V2 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
71.7%
66MiMo 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%
67MiMo V2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.7%
68MiMo 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%
69Qwen3.6 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
71.3%
70Qwen3.6 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%
71DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.2%
72DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.2%
73DeepSeek 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%
74DeepSeek 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%
75DeepSeek 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%
76Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
69.3%
77Qwen3.5 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%
78DeepSeek 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%
79NVIDIA 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. claim
Values from 2 sources
67.7%
80Nemotron 3 Ultra· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
67.7%
81Nemotron 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%
82Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
67.2%
83Qwen3.6 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%
84GLM 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.7%
85Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.7%
86Qwen3 Coder Next· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim64.3%
87Laguna XS 2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
63.1%
88Devstral 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%
89Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.1%
90DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.9%
91Laguna XS.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim57.7%
92MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.56.5%
93Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.7%
94DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.5%
95Kimi K2 Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
47.3%
96Nemotron 3 Super 120B A12B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
45.8%
97Nemotron 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%
98Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim41.9%
99Nemotron 3.5 Lightning 30B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
39.3%
100Nemotron 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.