Skip to content
aiqbench

OpenAI · model passport

OpenAI: GPT-6 Sol

gpt-6-sol
  • Cloud only
  • Proprietary licence
  • 1,050,000 context
  • Released 2026-10-09(first seen on LMArena)
15/27axes covered
Overall · LMArena
1,459#54 of 396
Best percentile
100.0AIME (math)
Cohort standing
79.0median 60.5

What the data says

Benchmarked on 15 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 100 pct — AIME (math) (100.0%)
  • 96.4 pct — GPQA Diamond (94.3%)
  • 95.7 pct — WebDev Arena (1,686)

Uneven: 51.2 percentile points between its best and worst axis — 100 pct on AIME (math) versus 48.8 pct on Factuality Arena.

  • AIME (math)100 pct100.0%Verify →
  • GPQA Diamond96.4 pct94.3%Verify →
  • WebDev Arena95.7 pct1,686Verify →
  • ARC-AGI-293.3 pct89.6%Verify →
  • Coding91.3 pct1,518Verify →
  • Agent Arena89.1 pct0.112Verify →
  • Hard prompts87.4 pct1,484Verify →
  • Overall86.6 pct1,459Verify →
  • Instruction following86.6 pct1,451Verify →
  • Search Arena85.7 pct1,228Verify →
  • SimpleQA Verified82.9 pct60.7%Verify →
  • Vision Arena80.7 pct1,270Verify →
  • Terminal-Bench 4.073.9 pct49.4%Verify →
  • HHEM Hallucination (Vectara)73.3 pct93.5%Verify →
  • Factuality Arena48.8 pct1,437Verify →
  • Document ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)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-6-sol
Context length1,050,000 tokens
Max output128,000 tokens
Acceptsfile, image, text
Input price$2 per 1M tokens
Cached input price$0.20 per 1M tokens
Output price$10 per 1M tokens

API parameters this endpoint supports

Include reasoningMax completion tokensMax tokensReasoningReasoning effortResponse formatSeedStructured outputsTool choiceTool callingVerbosity

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-6-sol","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-6-sol-max stands at 79 (raw mean 84.8) — measured on 15 of 27 axes.

    standingtemplateVerify →

  • gpt-6-sol-max stands at 79 versus a cohort median of 60.5 across 172 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 →