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
101Seed 2.0 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.5%
102MiMo 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
73.4%
103MiMo 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.73.4%
104Qwen3.6 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
73.4%
105Qwen3.6 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.73.4%
106Claude Haiku 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
107Claude Haiku 4.5launch-page setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.3%
108DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.1%
109DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
73.1%
110DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · DeepSeek internal code-agent framework· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.1%
111DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.1%
112Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
113Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.7%
114Claude Sonnet 4pass@1 · bash/editor tools · no extended thinking · avg@10 · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.7%
115MAI-Code-1.1-Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.6%
116Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.5%
117Claude Opus 4pass@1 · bash/editor tools · no extended thinking · avg@10 · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.5%
118Qwen3.5 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
72.4%
119Devstral 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.72.2%
120ling-2.6-1t· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
121DeepSeek 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.72.1%
122Qwen3.5 122B-A10B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
72%
123Nemotron 3 Ultra· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
71.9%
124Kimi K2 Thinking· 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%
125NVIDIA 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
71.1%
126Laguna 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
70.9%
127Grok Code Fast 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.8%
128Nemotron 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.70.7%
129Qwen3 Coder 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
70.6%
130Solar Pro 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.6%
131Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.3%
132LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70%
133Laguna XS.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim69.9%
134Qwen3 Coder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.6%
135Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.6%
136MiniMax M2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
69.4%
137Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
69.2%
138OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.1%
139o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.1%
140GLM 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68%
141DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.8%
142North Mini Code 1.0· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
67.6%
143Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.2%
144DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66%
145Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.8%
146Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.5%
147Nova 2 LiteAmazon Nova 2 Lite official launch chart / technical report · inference-time scaling · internal agentic scaffold, v1· Reported by Amazon Web Services, Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.5%
148GLM 4.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
64.2%
149Trinity Large ThinkingTrinity-Large-Thinking Model Card · mini-swe-agent-v2· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.2%
150openPangu 2.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim63.1%

Showing 101–150 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)