Skip to content

Benchmark

DeepSWE 1.1

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
55
Scores recorded
55
Sources
1
IQ weight
2.55

Score distribution

62.4%
Mean
66.9%
Median
14.1%
Std dev
42.2%
10th percentile
75.4%
90th percentile
12%
Min
12%79%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.55 for chat models, measured over 55 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Muse Wonder Full· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79%
2Muse Wonder· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.8%
3Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.8%
4Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.9%
5DeepSeek V4.1 Flash 1017· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77%
6Muse Spark 1.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.4%
7GPT-6.1 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.2%
8Ember-1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.2%
9Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.3%
10Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.2%
11DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.2%
12GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.1%
13Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
14MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
15GPT-5.6 Sol· LLM Stats data73%
16MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.9%
17ERNIE 5.5 Flash Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.2%
18Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
19Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
20Claude Fable 5· LLM Stats data70%
21GPT-5.6 Terra· LLM Stats data70%
22Kimi K3· LLM Stats data69%
23Claude Opus 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.8%
24GPT-6 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68.8%
25MiMo V2.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.9%
26GPT 5.5· LLM Stats data67%
27GPT-5.6 Luna· LLM Stats data67%
28GLM 5.3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.9%
29GPT-6 Luna· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.6%
30Grok 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.9%
31Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.3%
32Hy4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.6%
33LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.6%
34GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.4%
35Mistral Large 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.7%
36Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim60%
37Muse Spark 1.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim59.3%
38Claude Opus 4.8· LLM Stats data59%
39Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.7%
40Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.7%
41Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.6%
42Claude Sonnet 5· LLM Stats data54%
43Grok 4.5· LLM Stats data54%
44Muse Spark 1.1· LLM Stats data53%
45GPT 5.4· LLM Stats data52%
46Gemini 3.6 Flash· LLM Stats data49%
47Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.2%
48GLM 5.2· LLM Stats data44%
49Beam 1.0 501B A23B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.3%
50Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.2%

Showing 1–50 of 55 results.

Data credits: Data by LLM Stats