Skip to content
Model Pareto

Claude Opus 5

AnthropicProprietaryanthropic.com ↗
Compare with nearest rivalsCompare with…
Input
$5.00/M tok
Output
$25/M tok
Blended
$10/M tok · 3:1
Speed
54tok/s
Context
1Mtokens

Previous generation (superseded by Opus 5.5).

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

LiveCodeBenchEstimated
~#3 of 20 (estimated)~91.3%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. ~#3Claude Opus 5Estimated91.3%
  4. #3Qwen3.8 27B90.3%
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#3 of 126 (estimated)~82.8%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. ~#3Claude Opus 5Estimated82.8%
  4. #3Qwen3.8-Omni-Flash81.5%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~92.2%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Claude Opus 5Estimated92.2%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#4 of 531483 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #3Muse Spark 1.3Few votes1487
  4. #4Claude Opus 51483
  5. #4Gemini 3.8 FlashFew votes1483
lmarena.ai · 2026-09-25
LMArena Text (Elo)Verified
#3 of 531493 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #3Claude Opus 51493
  4. #3Gemini 3.8 Flash1493
lmarena.ai · 2026-09-24

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Opus 5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#2 of 9 (estimated)~84.9%
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Claude Opus 5Estimated84.9%
  3. #2Kimi K384.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~90.7%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Claude Opus 5Estimated90.7%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.9%
  1. #1Inkling97.1%
  2. ~#2Claude Opus 5Estimated96.9%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.3%
  1. #1Step 3.7 Flash98.5%
  2. ~#2Claude Opus 5Estimated98.3%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#3 of 12 (estimated)~84.0%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Claude Opus 5Estimated84.0%
  4. #3Nex-N2.5-Pro82.2%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~55.3%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Claude Opus 5Estimated55.3%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
Not comparable across labs (1)

Kept for reference, not counted in rankings: these use a lab-specific task set, answer key or scoring, so scores can't be compared fairly across labs. Only published scores are shown.