- input
- $0.30
- cached
- $0.006
- output
- $1.20
- Context
- 1Mtokens
- Released
- 2mo ago
- Size
- 763Bparameters
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 #37
- 1480
MiMo-V2.6-ProSimilar price - 1475
GPT-5.4Nearby rank - 1475
GLM 5.2Nearby rank - 1475
DeepSeek V4.1 Flash - 1474GLM 5.3 FlashNearby rank
- 1474GPT-6 AstraNearby rank
- 1455
Qwen3.7 PlusSimilar price - 1436
MiniMax M3Similar price - 1425DeepSeek V3.2Predecessor
- 1327
Llama 4 MaverickSimilar price
+50 vs DeepSeek V3.2 (predecessor) · Ahead of 3 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #30
- 1624MiMo-V2.6-ProSimilar price
- 1624
Qwen3.8 Flash NextNearby rank - 1622GLM 5.3Nearby rank
- 1621DeepSeek V4.1 Flash
- 1618
Grok 4.6Nearby rank - 1615GPT-5.6 SolNearby rank
- 1484MiniMax M3Similar price
- 1437
Beam 1.0 501B A23BSimilar price - 1362DeepSeek V3.2Predecessor
- 1256
Gemini 3.1 Flash Lite PreviewSimilar price
+258 vs DeepSeek V3.2 (predecessor) · Ahead of 3 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Arena #42
- 1265
Kimi K2.6Nearby rank - 1263Grok 4.6Nearby rank
- 1263DeepSeek V4.1 Flash
- 1263
Claude Sonnet 5.5Nearby rank - 1262Qwen3.7 PlusSimilar price
- 1247MiMo-V2.6-ProSimilar price
- 1232MiniMax M3Similar price
- 1145Llama 4 MaverickSimilar price
Ahead of 2 of 4 similarly priced models
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Agent Arena
Best IPS score per model · Higher is better
Not ranked on Agent Arena yet
ARC-AGI-2
Best score per model · Higher is better
#24 of 85
- 75.8%Claude Opus 4.7Nearby rank
- 74.0%GPT-5.4Nearby rank
- 72.9%DeepSeek V4.1 Flash
- 72.1%Claude Opus 4.8Nearby rank
- 72.1%Gemini 3.5 FlashNearby rank
- 42.4%Qwen3.8 27BSimilar price
- 5.7%GPT-5.4 NanoSimilar price
- 4.9%MiniMax M2.5Similar price
- 4.0%DeepSeek V3.2Predecessor
- 0.0%Llama 4 MaverickSimilar price
+68.9 pts vs DeepSeek V3.2 (predecessor) · Ahead of 4 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#38 of 72
- 29.3%GLM 5.3Similar price
- 26.8%Claude Opus 4.6Nearby rank
- 26.8%DeepSeek V4 Pro 0813Nearby rank
- 26.8%DeepSeek V4.1 Flash
- 26.8%Gemini 3.1 Pro PreviewNearby rank
- 26.8%Gemini 3.5 FlashNearby rank
- 17.1%
Inkling SmallSimilar price - 12.2%GPT-5.4 NanoSimilar price
- 0.0%Gemini 3.5 Flash LiteSimilar price
Ahead of 3 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#33 of 87
- 68.4%Gemini 3.8 FlashNearby rank
- 67.4%GPT-5.2Nearby rank
- 67.4%DeepSeek V4.1 Flash
- 66.0%Claude Opus 4.6Nearby rank
- 66.0%Grok 4.6Nearby rank
- 46.3%Inkling SmallSimilar price
- 44.9%GPT-5.4 NanoSimilar price
- 34.4%Qwen3.7 PlusSimilar price
- 27.7%Gemini 3.1 Flash LiteSimilar price
Ahead of 4 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#46 of 161
- 90.9%MiniMax M3Similar price
- 90.2%GLM 5.3 FlashNearby rank
- 89.9%GLM 5.1Nearby rank
- 89.8%DeepSeek V4.1 Flash
- 89.6%Claude Haiku 5.5Nearby rank
- 89.4%Gemini 3 Flash PreviewNearby rank
- 87.9%Qwen3.7 PlusSimilar price
- 81.8%Gemini 3.1 Flash LiteSimilar price
- 78.5%GPT-5.4 NanoSimilar price
Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#24 of 158
- 98.6%DeepSeek V4 Pro 0813Nearby rank
- 98.3%Claude Opus 4.8Nearby rank
- 98.3%DeepSeek V4.1 Flash
- 98.3%
Mistral Large 4Nearby rank - 98.3%GPT-5.6 LunaNearby rank
- 93.3%Qwen3.7 PlusSimilar price
- 87.8%GPT-5.4 NanoSimilar price
- 80.0%Gemini 3.1 Flash LiteSimilar price
- 71.1%MiniMax M3Similar price
Ahead of 4 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#47 of 87
- 44.1%Qwen3.6 PlusNearby rank
- 43.2%GPT-5.6 TerraNearby rank
- 42.9%DeepSeek V4.1 Flash
- 42.5%DeepSeek V4.1 Flash 1017Nearby rank
- 41.4%GPT-6 LunaNearby rank
- 41.0%GLM 5.3Similar price
- 19.1%Inkling SmallSimilar price
- 15.9%Qwen3.6 FlashSimilar price
- 11.7%GPT-5.4 NanoSimilar price
Ahead of 4 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.
Reasoning effort
ARC-AGI-2
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #371475
+50 vs DeepSeek V3.2 (predecessor)
- max147595% CI 1469 to 1481 · 13,580 votes
- Arena WebDevArena #301621
+258 vs DeepSeek V3.2 (predecessor)
- max162195% CI 1609 to 1632 · 3,400 votes
- Arena VisionArena #421263
- max126395% CI 1253 to 1273 · 4,247 votes
- ARC-AGI-2#24 of 8572.9%
+68.9 pts vs DeepSeek V3.2 (predecessor)
- none1.3%
- low60.6%
- high67.5%
- max72.9%
- FrontierMath-Tier-4-v2-Private#38 of 7226.8%
- max26.8%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#33 of 8767.4%
- max67.4%
Source:Epoch AI evaluation - GPQA diamond#46 of 16189.8%
- max89.8%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#24 of 15898.3%
- max98.3%
Source:Epoch AI evaluation - SimpleQA Verified#47 of 8742.9%
- max42.9%
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.