Skip to content
aiqbench

OpenAI · model passport

OpenAI: GPT-5.6 Terra

gpt-5-6-terra
  • Cloud only
  • Proprietary licence
  • 1,050,000 context
  • Released 2026-09-13(first seen on LMArena)
16/27axes covered
Overall · LMArena
1,466#45 of 396
Best percentile
94.0AIME (math)
Cohort standing
71.5median 60.3

What the data says

Benchmarked on 16 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 94 pct — AIME (math) (99.7%)
  • 92.8 pct — GPQA Diamond (93.3%)
  • 90.3 pct — Coding (1,517)

Uneven: 54.9 percentile points between its best and worst axis — 94 pct on AIME (math) versus 39.1 pct on Terminal-Bench 4.0.

  • AIME (math)94 pct99.7%Verify →
  • GPQA Diamond92.8 pct93.3%Verify →
  • Coding90.3 pct1,517Verify →
  • Instruction following89.9 pct1,464Verify →
  • Hard prompts89.4 pct1,489Verify →
  • Overall88.9 pct1,466Verify →
  • ARC-AGI-285.4 pct83.9%Verify →
  • Factuality Arena84.3 pct1,468Verify →
  • IFBench (Artificial Analysis)84.3 pct71.2%Verify →
  • Vision Arena80 pct1,268Verify →
  • Document Arena73.7 pct1,477Verify →
  • WebDev Arena69.1 pct1,522Verify →
  • SimpleQA Verified50 pct43.2%Verify →
  • SimpleBench49.4 pct48.9%Verify →
  • Agent Arena47.3 pct0.004Verify →
  • Terminal-Bench 4.039.1 pct21.5%Verify →
  • Search ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • Humanity's Last ExamNot 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
  • 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-5.6-terra
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$12 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-5.6-terra","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-5.6-terra-xhigh stands at 71.5 (raw mean 75.5) — measured on 16 of 27 axes.

    standingtemplateVerify →

  • gpt-5.6-terra-xhigh stands at 71.5 versus a cohort median of 60.3 across 176 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 →