- input
- $0.65
- cached
- $0.15
- output
- $3.41
- Context
- 262Ktokens
- Released
- 6mo ago
- Size
- 1Tparameters
Cost/1M tokens
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.
How it ranks
Against its predecessor, similarly priced models and the models ranked around it.
DeepSWE 1.1
Best pass@1 per model · Higher is better
Not evaluated in DeepSWE 1.1
Arena Text
Best Arena rating per model · Higher is better
Arena #61
- 1489
Gemini 3.7 FlashSimilar price - 1464
DeepSeek V4 Pro 0813Nearby rank - 1461
Claude Sonnet 5Nearby rank - 1461
Kimi K2.6 - 1460
Qwen3.6 Max PreviewNearby rank - 1458DeepSeek V4 Pro 0423Nearby rank
- 1450Kimi K2.5Predecessor
- 1448
Step 5 PreviewSimilar price - 1441
Qwen3.5 397B A17BSimilar price - 1290
Nova Pro 1.0Similar price
+11 vs Kimi K2.5 (predecessor) · Ahead of 3 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #66
- 1588Gemini 3.7 FlashSimilar price
- 1581DeepSeek V4 Pro 0813Similar price
- 1573Step 5 PreviewSimilar price
- 1515Qwen3.7 MaxNearby rank
- 1512
GPT-5.5Nearby rank - 1509Kimi K2.6
- 1508
GLM 5.1Nearby rank - 1506
Hy3Nearby rank - 1436Kimi K2.5Predecessor
- 1400Qwen3.5 397B A17BSimilar price
+73 vs Kimi K2.5 (predecessor) · Ahead of 1 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #40
- 1294Gemini 3.7 FlashSimilar price
- 1266Gemini 3.5 Flash LiteNearby rank
- 1265Gemma 4 31BNearby rank
- 1265Kimi K2.6
- 1263
Grok 4.6Nearby rank - 1263DeepSeek V4.1 FlashNearby rank
- 1252Kimi K2.5Predecessor
- 1246Qwen3.5 397B A17BSimilar price
- 1245Step 5 PreviewSimilar price
- 1019Nova Pro 1.0Similar price
+13 vs Kimi K2.5 (predecessor) · Ahead of 3 of 4 similarly priced models
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Arena Document
Best Arena rating per model · Higher is better
Arena #33
- 1480
Muse Spark 1.1Similar price - 1468Gemini 3.7 FlashSimilar price
- 1452Gemma 4 31BNearby rank
- 1451Gemini 3 Pro PreviewNearby rank
- 1450Kimi K2.6
- 1450Grok 4.6Nearby rank
- 1448Claude Sonnet 4.5Nearby rank
- 1438Kimi K2.5Predecessor
- 1419Claude Haiku 4.5Similar price
- 1406GLM 5V TurboSimilar price
Level with Kimi K2.5 (predecessor, overlapping 95% CIs) · Ahead of 2 of 4 similarly priced models
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#7 of 58
- 40.7%GPT-5.2Nearby rank
- 39.0%Gemini 3.5 FlashNearby rank
- 39.0%Kimi K2.6
- 37.6%Gemini 3 Pro PreviewNearby rank
- 36.9%Gemini 3.1 Pro PreviewNearby rank
- 35.6%Gemini 3 Flash PreviewSimilar price
- 28.3%GPT-5.4 MiniSimilar price
- 16.4%GLM 5Similar price
- 8.5%Qwen3 235B A22B Thinking 2507Similar price
Ahead of 4 of 4 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#10 of 46
- 14.6%GPT-5 ProNearby rank
- 14.6%Gemini 3.5 FlashNearby rank
- 14.6%Kimi K2.6
- 12.5%GPT-5Nearby rank
- 12.5%GPT-5.1Nearby rank
- 4.2%Gemini 3 Flash PreviewSimilar price
- 2.1%GLM 5Similar price
- 2.1%GPT-5.4 MiniSimilar price
- 0.0%Qwen3 235B A22B Thinking 2507Similar price
Ahead of 4 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#44 of 72
- 36.6%Gemini 3.7 FlashSimilar price
- 26.8%DeepSeek V4 Pro 0813Similar price
- 26.8%Gemini 3.5 FlashNearby rank
- 26.8%
Mistral Large 4Nearby rank - 25.6%Kimi K2.6
- 24.4%DeepSeek V4 Flash 0731Nearby rank
- 24.4%Grok 4.5Nearby rank
- 14.6%Grok 4.3Similar price
- 9.8%GPT-5.4 MiniSimilar price
Ahead of 2 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#46 of 87
- 71.6%Gemini 3.7 FlashSimilar price
- 64.6%DeepSeek V4 Pro 0813Similar price
- 58.6%Mistral Large 4Nearby rank
- 57.5%DeepSeek V4 Flash 0731Nearby rank
- 57.2%Kimi K2.6
- 57.2%Grok 4.5Nearby rank
- 55.8%GPT-5 ProNearby rank
- 42.8%Grok 4.3Similar price
- 31.2%Qwen3.5 397B A17BSimilar price
Ahead of 2 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#37 of 161
- 94.8%Gemini 3.7 FlashSimilar price
- 91.7%DeepSeek V4 Pro 0813Similar price
- 90.9%Qwen3.7 MaxNearby rank
- 90.9%GLM 5.3Nearby rank
- 90.8%Kimi K2.6
- 90.7%GPT-5.5Nearby rank
- 90.6%Claude Opus 5.5Nearby rank
- 87.8%GLM 5Similar price
- 86.4%Qwen3.5 397B A17BSimilar price
Ahead of 2 of 4 similarly priced models
OSWorld 2.0
Best score per model · Higher is better
#7 of 9
- 9.3%Claude Sonnet 4.6Nearby rank
- 4.6%
MiniMax M3Nearby rank - 4.6%Kimi K2.6
- 2.8%Qwen3.7 PlusNearby rank
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#35 of 158
- 98.6%DeepSeek V4 Pro 0813Similar price
- 97.2%Gemini 3.7 FlashSimilar price
- 97.2%Kimi K3Nearby rank
- 96.7%DeepSeek V4 Pro 0423Nearby rank
- 96.1%Kimi K2.6
- 96.1%GPT-5.2Nearby rank
- 95.6%Gemini 3.1 Pro PreviewNearby rank
- 88.9%Qwen3.5 397B A17BSimilar price
- 80.0%GLM 5Similar price
Ahead of 2 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#57 of 87
- 69.2%Gemini 3.7 FlashSimilar price
- 52.9%DeepSeek V4 Pro 0813Similar price
- 40.4%Qwen3 235B A22B Thinking 2507Similar price
- 36.5%Kimi K2.7 CodeNearby rank
- 35.5%Claude Sonnet 4.6Nearby rank
- 34.9%Kimi K2.6
- 34.3%Kimi K2.5Predecessor
- 34.2%GLM 5.2Nearby rank
- 33.2%Grok 4.3Similar price
+0.6 pts vs Kimi K2.5 (predecessor) · Ahead of 1 of 4 similarly priced models
SWE-bench Verified
Best score per model · Higher is better
#7 of 35
- 77.6%DeepSeek V4 Pro 0423Similar price
- 77.3%Qwen3.7 MaxSimilar price
- 76.7%Qwen3.6 Max PreviewNearby rank
- 76.7%Claude Opus 4.5Nearby rank
- 76.7%Kimi K2.6
- 75.6%Claude Opus 4.6Nearby rank
- 75.6%Gemini 3.1 Pro Preview Custom ToolsNearby rank
- 75.4%Gemini 3 Flash PreviewSimilar price
- 73.8%Kimi K2.5Predecessor
- 72.1%GLM 5Similar price
+2.9 pts vs Kimi K2.5 (predecessor) · Ahead of 2 of 4 similarly priced models
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
All published scores
- Arena TextArena #611461
+11 vs Kimi K2.5 (predecessor)
- default146195% CI 1456 to 1465 · 39,573 votes
- Arena WebDevArena #661509
+73 vs Kimi K2.5 (predecessor)
- default150995% CI 1502 to 1517 · 10,012 votes
- Arena VisionArena #401265
+13 vs Kimi K2.5 (predecessor)
- default126595% CI 1258 to 1272 · 16,265 votes
- Arena DocumentArena #331450
Level with Kimi K2.5 (predecessor, overlapping 95% CIs)
- default145095% CI 1443 to 1458 · 11,809 votes
- FrontierMath-2025-02-28-Private#7 of 5839.0%
- default39.0%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#10 of 4614.6%
- default14.6%
Source:Epoch AI evaluation - FrontierMath-Tier-4-v2-Private#44 of 7225.6%
- default25.6%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#46 of 8757.2%
- default57.2%
Source:Epoch AI evaluation - GPQA diamond#37 of 16190.8%
- default90.8%
Source:Epoch AI evaluation - OSWorld 2.0#7 of 94.6%
- default4.6%
- OTIS Mock AIME 2024-2025#35 of 15896.1%
- default96.1%
Source:Epoch AI evaluation - SimpleQA Verified#57 of 8734.9%
+0.6 pts vs Kimi K2.5 (predecessor)
- default34.9%
Source:Epoch AI evaluation - SWE-bench Verified#7 of 3576.7%
+2.9 pts vs Kimi K2.5 (predecessor)
- default76.7%
Source:Epoch AI evaluation
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.