Skip to content
aiqbench

OpenAI · model passport

OpenAI: GPT-4 Turbo

gpt-4-turbo
  • Cloud only
  • Proprietary licence
  • 128,000 context
  • Released 2024-04-09(curated)
11/27axes covered
Overall · LMArena
1,325#233 of 396
Best percentile
48.5LiveBench
Cohort standing
36.6median 32.8

What the data says

Benchmarked on 11 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 32.4 percentile points between its best and worst axis — 48.5 pct on LiveBench versus 16.1 pct on SimpleBench.

  • LiveBench48.5 pct52.9%Verify →
  • Overall41.4 pct1,325Verify →
  • Instruction following39.9 pct1,303Verify →
  • MMLU-Pro (Artificial Analysis)39 pct69.4%Verify →
  • LiveCodeBench (Artificial Analysis)37.4 pct29.1%Verify →
  • Hard prompts35.6 pct1,316Verify →
  • Coding35.3 pct1,347Verify →
  • GPQA Diamond28.5 pct46.6%Verify →
  • Vision Arena21.3 pct1,112Verify →
  • AIME (math)19.5 pct6.7%Verify →
  • SimpleBench16.1 pct25.1%Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Use it hosted

API model IDopenai/gpt-4-turbo
Context length128,000 tokens
Max output4,096 tokens
Acceptstext, image
Input price$10 per 1M tokens
Output price$30 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasLogprobsMax tokensPresence penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop logprobsTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4-turbo","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • gpt-4-turbo-2024-04-09 stands at 36.6 (raw mean 33) — measured on 11 of 27 axes.

    standingtemplateVerify →

  • gpt-4-turbo-2024-04-09 stands at 36.6 versus a cohort median of 32.8 across 117 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →