- input
- $0.1875
- output
- $1.125
- cache write
- $0.2344
- Context
- 1Mtokens
- Released
- 6mo ago
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
Not ranked on Arena Text yet
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev yet
Arena Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision yet
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
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#31 of 58
- 27.2%
GPT-5 MiniSimilar price - 25.9%GPT-5.4 NanoSimilar price
- 14.1%
Gemini 2.5 ProNearby rank - 10.3%Gemini 2.5 Pro Preview 06-05Nearby rank
- 10.3%
Qwen3.6 Flash - 8.5%Qwen3 235B A22B Thinking 2507Nearby rank
- 8.3%GPT-5 NanoNearby rank
- 6.2%Qwen3.5-FlashPredecessor
- 1.7%
DeepSeek V3Similar price - 0.3%
Mistral Medium 3Similar price
+4.1 pts vs Qwen3.5-Flash (predecessor) · Ahead of 2 of 4 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#39 of 46
- 8.3%Qwen3.6 PlusSimilar price
- 6.3%GPT-5 MiniSimilar price
- 6.3%GPT-5.4 NanoSimilar price
- 0.0%Qwen3 235B A22B Thinking 2507Nearby rank
- 0.0%Qwen3.5-FlashPredecessor
- 0.0%Qwen3.6 Flash
- 0.0%
GLM 4.7Nearby rank
Level with Qwen3.5-Flash (predecessor) · Ahead of 0 of 3 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#76 of 87
- 82.1%GPT-5.6 LunaSimilar price
- 68.8%GLM 5.3Similar price
- 67.4%DeepSeek V4.1 FlashSimilar price
- 27.7%Gemini 3.1 Flash LiteSimilar price
- 24.6%Gemini 2.5 ProNearby rank
- 23.9%
Claude Sonnet 4.5Nearby rank - 22.5%Qwen3.6 Flash
- 20.4%Qwen3.6 35B A3BNearby rank
- 20.0%GPT-5 NanoNearby rank
- 18.2%Qwen3.5-FlashPredecessor
+4.2 pts vs Qwen3.5-Flash (predecessor) · Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#77 of 161
- 91.6%GPT-5.6 LunaSimilar price
- 90.9%
MiniMax M3Similar price - 90.9%GLM 5.3Similar price
- 83.4%DeepSeek ReasonerNearby rank
- 83.3%Gemini 3.5 Flash LiteNearby rank
- 83.3%Qwen3.6 Flash
- 83.3%GLM 4.7Nearby rank
- 82.5%GPT-5.5 InstantNearby rank
- 82.3%Qwen3.5-FlashPredecessor
- 71.2%DeepSeek V3Similar price
+1.0 pts vs Qwen3.5-Flash (predecessor) · Ahead of 1 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#77 of 158
- 98.3%GPT-5.6 LunaSimilar price
- 91.1%GLM 5.3Similar price
- 84.4%o3Nearby rank
- 84.4%Qwen3.5-FlashPredecessor
- 84.4%Qwen3.6 Flash
- 83.3%GLM 4.7Nearby rank
- 83.1%
Kimi K2 Thinking TurboNearby rank - 71.1%MiniMax M3Similar price
- 48.9%DeepSeek V3Similar price
Level with Qwen3.5-Flash (predecessor) · Ahead of 2 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#79 of 87
- 42.9%DeepSeek V4.1 FlashSimilar price
- 41.0%GPT-5.6 LunaSimilar price
- 41.0%GLM 5.3Similar price
- 20.3%Qwen3.5-FlashPredecessor
- 19.1%
Inkling SmallSimilar price - 17.4%
Seed 1.6Nearby rank - 15.9%Qwen3.6 Flash
- 13.2%Claude Haiku 4.5Nearby rank
- 12.7%GPT-4.1 MiniNearby rank
-4.4 pts vs Qwen3.5-Flash (predecessor) · Ahead of 0 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
- FrontierMath-2025-02-28-Private#31 of 5810.3%
+4.1 pts vs Qwen3.5-Flash (predecessor)
- default10.3%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#39 of 460.0%
Level with Qwen3.5-Flash (predecessor)
- default0.0%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#76 of 8722.5%
+4.2 pts vs Qwen3.5-Flash (predecessor)
- none22.5%
- default17.2%
Source:Epoch AI evaluation - GPQA diamond#77 of 16183.3%
+1.0 pts vs Qwen3.5-Flash (predecessor)
- default83.3%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#77 of 15884.4%
Level with Qwen3.5-Flash (predecessor)
- default84.4%
Source:Epoch AI evaluation - SimpleQA Verified#79 of 8715.9%
-4.4 pts vs Qwen3.5-Flash (predecessor)
- default15.9%
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.