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.

SpecificationLongCat 2.0MeituanClaude Opus 5Anthropic
ReleasedJul 20, 2026Jul 24, 2026
Context window1.05M1M
Max output262K128K
Input / 1M$0.3$5
Output / 1M$1.2$25
Cost per task$0.11$2.25
Arena Elo1,393
Serving providers15
Parameters1775.6BUndisclosed
LicencemitProprietary
Capabilities
  • Reasoning
  • Tool use
  • Open weights
  • 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

  • LongCat 2.0
  • Claude Opus 5
  • Intelligence Index

    LongCat 2.0
    33.9
    Claude Opus 5
    63.1
  • Coding Index

    LongCat 2.0
    45.3
    Claude Opus 5
    78.0
  • Agentic Index

    LongCat 2.0not measured
    Claude Opus 5
    59.2
  • Output speed

    LongCat 2.0
    27 t/s
    Claude Opus 5
    87 t/s
  • Context window

    LongCat 2.0
    1.05M
    Claude Opus 5
    1M
  • Latency · lower is better

    LongCat 2.0
    2.2s
    Claude Opus 5
    1.12s
  • Blended price / 1M · lower is better

    LongCat 2.0
    $0.525
    Claude Opus 5
    $10
  • Cost per task · lower is better

    LongCat 2.0
    $0.11
    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
MetricLongCat 2.0Claude Opus 5
Intelligence Index33.963.1
Coding Index45.378.0
Agentic Index59.2
Output speed27 t/s87 t/s
Context window1.05M1M
Latency · lower is better2.2s1.12s
Blended price / 1M · lower is better$0.525$10
Cost per task · lower is better$0.11$2.25

Evaluation scores

Percentage correct on a common 0–100% scale

  • LongCat 2.0
  • Claude Opus 5
  • GPQA Diamond

    LongCat 2.0
    78.0%
    Claude Opus 5
    93.2%
  • Humanity's Last Exam

    LongCat 2.0
    33.7%
    Claude Opus 5
    54.9%
  • SciCode

    LongCat 2.0
    35.4%
    Claude Opus 5
    55.7%
  • τ²-bench

    LongCat 2.0
    12.8%
    Claude Opus 5
    42.1%
  • AA-LCR long context

    LongCat 2.0
    62.7%
    Claude Opus 5
    75.7%

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

View as table
EvaluationLongCat 2.0Claude Opus 5
GPQA Diamond78.0%93.2%
Humanity's Last Exam33.7%54.9%
SciCode35.4%55.7%
τ²-bench12.8%42.1%
Terminal-Bench Hard
LiveCodeBench
AA-LCR long context62.7%75.7%
AIME 2025

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