Skip to content
llmwaves

Compare

Four models, one page

Pick the models you are actually choosing between. Every row is scaled within itself, so a bar means something next to its neighbours and nothing across rows.

SpecificationGPT-5.1OpenAIClaude Opus 5Anthropic
ReleasedNov 13, 2025Jul 24, 2026
Context window400K1M
Max output128K128K
Input / 1M$1.25$5
Output / 1M$10$25
Cost per task$0.86$2.25
Arena Elo1,2321,393
Serving providers25
ParametersUndisclosedUndisclosed
LicenceProprietaryProprietary
Capabilities
  • Reasoning
  • Tool use
  • Vision
  • Reasoning
  • Tool use
  • Vision

Metrics side by side

Each row is scaled to the largest value in that row — bars compare within a row, never across rows

  • GPT-5.1
  • Claude Opus 5

  • Intelligence Index

    GPT-5.1
    37.5
    Claude Opus 5
    63.1

  • Coding Index

    GPT-5.1
    49.4
    Claude Opus 5
    78.0

  • Agentic Index

    GPT-5.1
    21.6
    Claude Opus 5
    59.2

  • Output speed

    GPT-5.1
    47 t/s
    Claude Opus 5
    87 t/s

  • Context window

    GPT-5.1
    400K
    Claude Opus 5
    1M

  • Latency · lower is better

    GPT-5.1
    542ms
    Claude Opus 5
    1.12s

  • Blended price / 1M · lower is better

    GPT-5.1
    $3.44
    Claude Opus 5
    $10

  • Cost per task · lower is better

    GPT-5.1
    $0.86
    Claude Opus 5
    $2.25

Rows marked “lower is better” still draw a longer bar for a larger number — read the value, not just the length. Arena Elo is in the specification table above instead: it has no meaningful zero, so a bar would flatten the gaps.

View as table
MetricGPT-5.1Claude Opus 5
Intelligence Index37.563.1
Coding Index49.478.0
Agentic Index21.659.2
Output speed47 t/s87 t/s
Context window400K1M
Latency · lower is better542ms1.12s
Blended price / 1M · lower is better$3.44$10
Cost per task · lower is better$0.86$2.25

Evaluation scores

Percentage correct on a common 0–100% scale

  • GPT-5.1
  • Claude Opus 5

  • GPQA Diamond

    GPT-5.1
    87.3%
    Claude Opus 5
    93.2%

  • Humanity's Last Exam

    GPT-5.1
    28.5%
    Claude Opus 5
    54.9%

  • SciCode

    GPT-5.1
    43.3%
    Claude Opus 5
    55.7%

  • τ²-bench

    GPT-5.1
    81.9%
    Claude Opus 5
    42.1%

  • Terminal-Bench Hard

    GPT-5.1
    45.5%
    Claude Opus 5not measured

  • LiveCodeBench

    GPT-5.1
    86.8%
    Claude Opus 5not measured

  • AA-LCR long context

    GPT-5.1
    76.7%
    Claude Opus 5
    75.7%

  • AIME 2025

    GPT-5.1
    94.0%
    Claude Opus 5not measured

A missing bar means that evaluation was not run for that model — it is not a zero.

View as table
EvaluationGPT-5.1Claude Opus 5
GPQA Diamond87.3%93.2%
Humanity's Last Exam28.5%54.9%
SciCode43.3%55.7%
τ²-bench81.9%42.1%
Terminal-Bench Hard45.5%—
LiveCodeBench86.8%—
AA-LCR long context76.7%75.7%
AIME 202594.0%—

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).