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.

SpecificationGemini 2.5 ProGoogleClaude Opus 5Anthropic
ReleasedJun 17, 2025Jul 24, 2026
Context window1.05M1M
Max output66K128K
Input / 1M$1.25$5
Output / 1M$10$25
Cost per task$0.86$2.25
Arena Elo1,2731,393
Serving providers25
ParametersUndisclosedUndisclosed
LicenceProprietaryProprietary
Capabilities
  • Reasoning
  • Tool use
  • Vision
  • Audio in
  • Video in
  • 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

  • Gemini 2.5 Pro
  • Claude Opus 5
  • Intelligence Index

    Gemini 2.5 Pro
    25.9
    Claude Opus 5
    63.1
  • Coding Index

    Gemini 2.5 Pro
    33.3
    Claude Opus 5
    78.0
  • Agentic Index

    Gemini 2.5 Pro
    7.2
    Claude Opus 5
    59.2
  • Output speed

    Gemini 2.5 Pro
    106 t/s
    Claude Opus 5
    87 t/s
  • Context window

    Gemini 2.5 Pro
    1.05M
    Claude Opus 5
    1M
  • Latency · lower is better

    Gemini 2.5 Pro
    2.32s
    Claude Opus 5
    1.12s
  • Blended price / 1M · lower is better

    Gemini 2.5 Pro
    $3.44
    Claude Opus 5
    $10
  • Cost per task · lower is better

    Gemini 2.5 Pro
    $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
MetricGemini 2.5 ProClaude Opus 5
Intelligence Index25.963.1
Coding Index33.378.0
Agentic Index7.259.2
Output speed106 t/s87 t/s
Context window1.05M1M
Latency · lower is better2.32s1.12s
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

  • Gemini 2.5 Pro
  • Claude Opus 5
  • GPQA Diamond

    Gemini 2.5 Pro
    84.4%
    Claude Opus 5
    93.2%
  • Humanity's Last Exam

    Gemini 2.5 Pro
    22.5%
    Claude Opus 5
    54.9%
  • SciCode

    Gemini 2.5 Pro
    42.8%
    Claude Opus 5
    55.7%
  • τ²-bench

    Gemini 2.5 Pro
    54.1%
    Claude Opus 5
    42.1%
  • Terminal-Bench Hard

    Gemini 2.5 Pro
    26.5%
    Claude Opus 5not measured
  • LiveCodeBench

    Gemini 2.5 Pro
    80.1%
    Claude Opus 5not measured
  • AA-LCR long context

    Gemini 2.5 Pro
    66.0%
    Claude Opus 5
    75.7%
  • AIME 2025

    Gemini 2.5 Pro
    87.7%
    Claude Opus 5not measured

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

View as table
EvaluationGemini 2.5 ProClaude Opus 5
GPQA Diamond84.4%93.2%
Humanity's Last Exam22.5%54.9%
SciCode42.8%55.7%
τ²-bench54.1%42.1%
Terminal-Bench Hard26.5%
LiveCodeBench80.1%
AA-LCR long context66.0%75.7%
AIME 202587.7%

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