Back to models
Intelligence Index
Standard setting
6.3#79 of 83measured models
Measured · Artificial Analysis v4.3.2- Context window
- 131.07K tok
Performance profile
ReasoningRank #82 of 107
63.1%
GPQA DiamondCodingRank #89 of 94
21.6%
SciCodeCost efficiencyRank #23 of 67
126.5pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)Celeris-1
Cost per task (USD) · log scale
Celeris-1Standard
- Intelligence Index
- 6.3
- Cost / task
- $0.0502
- Evaluation time
- 3.3s
Pricing & access
No API offering listed in our tracked sources.
Benchmarks
Full leaderboardSource (opens in a new tab)6.8%, rank 101 of 12621.6%, rank 89 of 940.0%, rank 56 of 8738.0%, rank 98 of 125302 Elo, rank 88 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 98Qwen3 Next 80B A3B InstructStandard7.6%
- 99Qwen3.5 Omni FlashStandard7.6%
- 100Qwen3 Omni 30B A3B (Reasoning)Reasoning7.5%
- 101Celeris-1Standard6.8%
- 102Granite 4.2 3BReasoning6.6%
- 103LFM2.5-2.6BReasoning6.2%
- 104Llama 3.2 Instruct 11B (Vision)Standard5.5%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherLlama 4 ScoutStandard
- Intelligence Index
- 6.5+0.1
- Cost / task
- $0.112+124%
- Higher score, lower costMistral Small 4Reasoning
- Intelligence Index
- 11.3+4.9
- Cost / task
- $0.015−70%
- Similar scoreMinistral 3 14BStandard
- Intelligence Index
- 6.0−0.3
- Cost / task
- $0.019−61%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.