Skip to content
aiqbench

Anthropic · model passport

Anthropic: Claude Sonnet 4.6

claude-sonnet-4-6
  • Cloud only
  • Proprietary licence
  • 1,000,000 context
  • Released 2026-09-13(first seen on LMArena)
17/27axes covered
Overall · LMArena
1,472#39 of 396
Best percentile
94.9Coding
Cohort standing
69.1median 60.3

What the data says

Benchmarked on 17 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 94.9 pct — Coding (1,528)
  • 94.7 pct — Instruction following (1,475)
  • 94.7 pct — Hard prompts (1,503)

Uneven: 57.1 percentile points between its best and worst axis — 94.9 pct on Coding versus 37.8 pct on SimpleQA Verified.

  • Coding94.9 pct1,528Verify →
  • Instruction following94.7 pct1,475Verify →
  • Hard prompts94.7 pct1,503Verify →
  • Overall90.4 pct1,472Verify →
  • Vision Arena82.7 pct1,275Verify →
  • Factuality Arena77.3 pct1,461Verify →
  • FrontierMath76.8 pct32.4%Verify →
  • Document Arena76.3 pct1,478Verify →
  • GPQA Diamond73.3 pct87.4%Verify →
  • WebDev Arena69.8 pct1,523Verify →
  • ARC-AGI-268.5 pct60.4%Verify →
  • Terminal-Bench68.2 pct53.4%Verify →
  • IFBench (Artificial Analysis)64.8 pct56.6%Verify →
  • AIME (math)63 pct85.8%Verify →
  • SWE-bench Verified59.4 pct75.2%Verify →
  • HHEM Hallucination (Vectara)39 pct89.4%Verify →
  • SimpleQA Verified37.8 pct35.5%Verify →
  • Search ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not 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 IDanthropic/claude-sonnet-4.6
Context length1,000,000 tokens
Max output128,000 tokens
Acceptstext, image, file
Input price$3 per 1M tokens
Cached input price$0.30 per 1M tokens
Output price$15 per 1M tokens

API parameters this endpoint supports

Include reasoningMax completion tokensMax tokensReasoningReasoning effortResponse formatStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop-pVerbosity

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-sonnet-4.6","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.

  • claude-sonnet-4-6 stands at 69.1 (raw mean 72.5) — measured on 17 of 27 axes.

    standingtemplateVerify →

  • claude-sonnet-4-6 stands at 69.1 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 →