Back to models
Intelligence Index
Reasoning setting
26.0#39 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 400K tok
Performance profile
ReasoningRank #48 of 107
82.3%
GPQA DiamondCodingRank #24 of 94
52.5%
SciCodeCost efficiencyRank #47 of 67
37.6pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)GPT-5.5 Instant (June 2026)
Cost per task (USD) · log scale
GPT-5.5 Instant (June 2026)June 2026
- Intelligence Index
- 26.0
- Cost / task
- $0.6915
- Evaluation time
- 33.3s
Pricing & access
No API offering listed in our tracked sources.
Benchmarks
Full leaderboardSource (opens in a new tab)19.9%, rank 65 of 12652.5%, rank 24 of 9412.6%, rank 25 of 8770.0%, rank 62 of 125509 Elo, rank 76 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 61Ling-3.0-flash-VLReasoning22.0%
- 63Ring-2.6-1TExtra high21.6%
- 64o3Reasoning20.1%
- 65GPT-5.5 Instant (June 2026)Reasoning19.9%
- 66gpt-oss-120bHigh19.6%
- 67Gemma 4 26B A4BReasoning19.3%
- 68Gemini 3.5 Flash-LiteHigh18.8%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherApodex 1.1Reasoning
- Intelligence Index
- 26.4+0.4
- Cost / task
- $0.464−33%
- Higher score, lower costMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+20.3
- Cost / task
- $0.133−81%
- More from OpenAIGPT-6 LunaMax
- Intelligence Index
- 38.1+12.1
- Cost / task
- $0.068−90%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.