o1-preview

deprecated by benchmark source

OpenAI · released 2024-09-12 · 0 offers

Context 128K tokens

Providers

No provider publishes an API price for this model yet, so no cost can be modeled.

4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one

14.1

AA Coding v4.x 34.0Coding Agent v1.4 —AA Intelligence (est.) 5.1AA Agentic —Epoch ECI 134.6Software ECI 137.3DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

6 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Composite attachments (used in the score, not counted as exact benchmarks):

WeirdML v210047.6%2026-09-10
WeirdML v2 → · Published board — Presents LLMs with unusual machine-learning tasks where they must write, run, and iteratively improve PyTorch code under fixed compute and time limits.
AA Coding Index v4.x · frozen 2026-10-274034.02026-10-27
AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).

AIME 2025 (AA)7579.7%2026-09-10
AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.

LLM Divergent Thinking Creativity Benchmark1004.792026-09-10
LLM Divergent Thinking Creativity Benchmark published 2026-09-10 → · Published board — Models generate 25 words maximally distinct from each other and from 50 seed words under starting-letter constraints, scored by LLM-judged word divergence.

SimpleBench7141.7%2026-09-10
SimpleBench published 2026-09-10 → · Published board — A multiple-choice text benchmark of over 200 questions covering spatio-temporal reasoning, social intelligence, and linguistic adversarial robustness, on which a non-specialized human baseline outperforms every tested LLM.
SimpleBench7141.7%2026-09-26
SimpleBench published 2026-09-26 → · Published board — A multiple-choice text benchmark of over 200 questions covering spatio-temporal reasoning, social intelligence, and linguistic adversarial robustness, on which a non-specialized human baseline outperforms every tested LLM.

GPQA Diamond (AA)6076.5%2026-09-10
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.

Missing coverage · 313 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.