Skip to content
Model Pareto

Kimi K3.1 Pro vs Claude Opus 5

Kimi K3.1 Pro scores higher than Claude Opus 5 in all 3 shared categories. Claude Opus 5 costs 2.5× as much as Kimi K3.1 Pro ($10.0 vs $4.00 per million tokens, blended 3:1 input:output).
Kimi K3.1 ProClaude Opus 5
Focus

Coding: quality vs price

Compared models are ringed; the other 131 ranked here are greyed.

Lower price is better. Pareto frontier: Nex-N2.5-Mini, Nex-N2.5-Pro, MiMo-V2.6-Flash, Ternary Bonsai 2 27B, MiMo-V2.6-Pro, Kimi K3.1 Pro, Claude Opus 5.5. 43 models are not plotted: Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B.

43 models with no price data — shown in the strip at the left edge

Muse Wonder Full, GLM-5.3 Flash NVFP4, DeepSeek V4.1 Flash NVFP4, DeepSeek-V4-Pro-0813-nvfp4-DSpark, GLM-5.3 NVFP4, Atria Dawn Preview, Ternary Bonsai 27B, Xing4.0-29B-A4B, Beam 1.0 501B A23B, Qwen3.8 27B NVFP4, Maple-Preview, Intern-S2-397B, Bonsai 27B, Solar Open2 250B, Muse Spark Open, Laguna S 2.1, Phi-4-reasoning-plus, Motif 3, Nex-N2-Pro, Flint, Nemotron 3.5 Super VL NVFP4, Nemotron 3.5 Super VL, K2 Horizon 375B A23B, K-EXAONE 2.0 0803, A.X-K2, Intern-S2-Preview (35B-A3B), Nemotron 3.5 Bolt 74B-A9B, K2 Horizon MoVA 36B A4B, G9v3-39A5B, North Mini Code, Qwen3.8 Flash-Next NVFP4, LFM2.5-24B-A2B, K2 Horizon 7B, K2-Horizon-32B, Devstral 2, NVIDIA Nemotron-Labs Dory1.0 4B, MiniCPM5-2B, Falcon-H1-34B-Instruct, Devstral Small 2, Ling 3.0 Tiny, K2 Horizon 3.7B, K2 Horizon 0.9B, LFM2.5-2.6B

  • Best-value frontier (nothing is both cheaper and better)
  • Evidencestrong → weak
  • Estimated from other categories
  • Kimi K3.1 Pro
    Quality
    92.9
    Rank
    #2/133
    Price
    $4.00/M tok
    Speed
    77tok/s
    In$2.00▾Out$10▾/M tok

    vs Claude Opus 5: +7.4 quality · 0.4× price

  • Claude Opus 5
    Quality
    85.5
    Rank
    #7/133
    Price
    $10.0/M tok
    Speed
    54tok/s
    In$5.00Out$25/M tok

    vs Kimi K3.1 Pro: −7.4 quality · 2.5× price

Overview

Metric
Kimi K3.1 Pro
Claude Opus 5
Lab
Moonshot AI (Kimi)
Anthropic
Released
Oct 23, 2026
Jul 24, 2026
Weights
Proprietary
Proprietary
Input price
$/M tok
$2.00Best
$5.00
Output price
$/M tok
$10Best
$25
Blended price
$/M tok · 3:1 in:out
$4.00Best
$10
Output speed
tok/s
77Best
54
Context
tokens
1MBest
1M

Quality by category

0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.

Metric
Kimi K3.1 Pro
Claude Opus 5
Coding
92.9±7.6Best
#2/133Verifiedbest value
85.5±3.2
#7/133Mixed
Writing & chat
Not ranked
89.4±4.3
#3/160Verified
Vision
82.3±8.2Best
#8/97Verified
76.9±4.8
#14/97Verified
Hard reasoning
93.3±5.1Best
#7/213Verified
91.8±3.7
#8/213Verified
Agents
Not ranked
84.4±4.6
#8/186Mixed

Coding benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Kimi K3.1 Pro
Claude Opus 5
SWE-bench Verified
day 0
~#2/20~92.6%Estimated
  1. #1Claude Opus 596.0%
  2. ~#2Kimi K3.1 ProEstimated92.6%
  3. #2Claude Sonnet 585.2%
estimated from related benchmarks
#1/1996.0%Lab-reported
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
anthropic.com · 2026-07-24
SWE-bench Pro (Public)
day 0
~#4/23~80.2%Estimated
  1. #1Claude Opus 5.589.9%
  2. #3Claude Fable 5.181.2%
  3. ~#4Kimi K3.1 ProEstimated80.2%
  4. #4Claude Opus 579.2%
estimated from related benchmarks
#4/2279.2%Lab-reported
  1. #1Claude Opus 5.589.9%
  2. #3Claude Fable 5.181.2%
  3. #4Claude Opus 579.2%
  4. #5Intern-S2-397B68.5%
anthropic.com · 2026-07-24
DeepSWE v1.1
day 0
~#5/43~74.5%Estimated
  1. #1Gemini 4 Argon78.8%
  2. #4Muse Wonder75.8%
  3. ~#5Kimi K3.1 ProEstimated74.5%
  4. #5DeepSeek V4.1 Flash74.2%
estimated from related benchmarks
#25/4262.5%Verified
  1. #1Gemini 4 Argon78.8%
  2. #24GLM-5.3 Flash63.4%
  3. #25Claude Opus 562.5%
  4. #26Step 5 Preview61.9%
artificialanalysis.ai · 2026-09-24
Terminal-Bench 4.0
day 0
#1/9867.2%BestVerified
  1. #1Kimi K3.1 Pro67.2%
  2. #2Claude Sonnet 5.563.6%
artificialanalysis.ai · 2026-10-24
#10/9849.0%Verified
  1. #1Kimi K3.1 Pro67.2%
  2. #8Muse Wonder52.0%
  3. #10Claude Opus 549.0%
  4. #11GPT-6 Sol43.9%
artificialanalysis.ai · 2026-09-24
LiveCodeBench
third-party
~#2/28~92.1%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2Kimi K3.1 ProEstimated92.1%
  3. #2Qwen3.8 Flash-Next91.9%
estimated from related benchmarks
~#5/28~89.9%Estimated
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #4Ternary Bonsai 2 27B90.1%
  3. ~#5Claude Opus 5Estimated89.9%
  4. #5Nemotron 3 Ultra89.0%
estimated from related benchmarks
SciCode
third-party
#7/11760.8%BestVerified
  1. #1Claude Opus 5.566.9%
  2. #6MiMo-V2.6-Pro60.9%
  3. #7Kimi K3.1 Pro60.8%
  4. #8Muse Wonder60.3%
artificialanalysis.ai · 2026-10-24
#21/11756.4%Verified
  1. #1Claude Opus 5.566.9%
  2. #20GPT-6 Astra56.5%
  3. #21Claude Opus 556.4%
  4. #22DeepSeek V4.1 Flash 101755.9%
artificialanalysis.ai · 2026-09-24
AA Coding Agent Index
third-party
~#4/24~58.7Estimated
  1. #1Claude Opus 5.561.7
  2. #3Muse Wonder Full58.9
  3. ~#4Kimi K3.1 ProEstimated58.7
  4. #4Claude Fable 5.157.6
estimated from related benchmarks
#2/2359.7Verified
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #3Muse Wonder Full58.9
artificialanalysis.ai · 2026-09-24
Benchmarks in other categories (4)

Writing & chat benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Kimi K3.1 Pro
Claude Opus 5

Vision benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Kimi K3.1 Pro
Claude Opus 5
MMMU
day 0
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Kimi K3.1 ProEstimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
~#2/3~71.3%Estimated
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Opus 5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
estimated from related benchmarks
MMMU-Pro
day 0
#6/8783.9%Verified
  1. #1Claude Opus 5.587.7%
  2. #5Claude Opus 584.7%
  3. #6Kimi K3.1 Pro83.9%
  4. #7GPT-6 Sol83.3%
artificialanalysis.ai · 2026-10-24
#5/8784.7%BestVerified
  1. #1Claude Opus 5.587.7%
  2. #4Gemini 3.8 Flash85.6%
  3. #5Claude Opus 584.7%
  4. #6Kimi K3.1 Pro83.9%
artificialanalysis.ai · 2026-09-24
CharXiv Reasoning
day 0
~#2/12~85.1%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Kimi K3.1 ProEstimated85.1%
  3. #2Kimi K384.8%
estimated from related benchmarks
~#2/12~85.1%Estimated
  1. #1Gemini 3.8 Flash86.2%
  2. ~#2Claude Opus 5Estimated85.1%
  3. #2Kimi K384.8%
estimated from related benchmarks
OmniDocBench v1.5
third-party
~#4/8~89.9%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Kimi K3.1 ProEstimated89.9%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
~#4/8~90.7%Estimated
  1. #1MiniMax-M391.6%
  2. #2Qwen3.8 27B91.1%
  3. ~#4Claude Opus 5Estimated90.7%
  4. #4Gemini 3.1 Pro85.3%
estimated from related benchmarks
GDP.pdf (AA)
third-party
~#12/47~22.3%Estimated
  1. #1Muse Wonder Full32.6%
  2. #10Qwen3.8 Max (0902)22.8%
  3. ~#12Kimi K3.1 ProEstimated22.3%
  4. #12Kimi K322.0%
estimated from related benchmarks
#13/4621.6%Verified
  1. #1Muse Wonder Full32.6%
  2. #12Kimi K322.0%
  3. #13Claude Opus 521.6%
  4. #14GPT-5.521.2%
artificialanalysis.ai · 2026-09-24
Chartography
third-party
~#7/24~39.2%Estimated
  1. #1GPT-6 Astra71.0%
  2. #6Gemini 3.8 Flash40.9%
  3. ~#7Kimi K3.1 ProEstimated39.2%
  4. #7GPT-5.6 Terra34.0%
estimated from related benchmarks
#12/2327.3%Verified
  1. #1GPT-6 Astra71.0%
  2. #11Muse Spark 1.327.6%
  3. #12Claude Opus 527.3%
  4. #13Kimi K326.6%
surgehq.ai · 2026-09-24

Hard reasoning benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Kimi K3.1 Pro
Claude Opus 5
GPQA Diamond
day 0
~#2/191~96.1%Estimated
  1. #1GPT-6 Astra96.1%
  2. ~#2Kimi K3.1 ProEstimated96.1%
  3. #2Gemini 3.8 Flash95.3%
estimated from related benchmarks
#11/19093.2%Verified
  1. #1GPT-6 Astra96.1%
  2. #5Step 5 Preview93.5%
  3. #11Claude Opus 593.2%
  4. #12MiniMax-M392.9%
artificialanalysis.ai · 2026-09-24
Humanity's Last Exam
day 0
#9/19752.5%Verified
  1. #1Claude Opus 5.561.4%
  2. #8GPT-6.1 Sol52.9%
  3. #9Kimi K3.1 Pro52.5%
  4. #10Muse Wonder50.1%
artificialanalysis.ai · 2026-10-24
#5/19754.9%BestVerified
  1. #1Claude Opus 5.561.4%
  2. #4Claude Sonnet 5.555.0%
  3. #5Claude Opus 554.9%
  4. #6GPT-6 Astra54.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)
day 0
~#2/33~99.1%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Kimi K3.1 ProEstimated99.1%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
~#2/33~99.4%Estimated
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Opus 5Estimated99.4%
  3. #2Beam 1.0 501B A23B97.7%
estimated from related benchmarks
AA Intelligence Index
third-party
#4/10055.1BestVerified
  1. #1Claude Opus 5.557.6
  2. #3Muse Wonder Full55.8
  3. #4Kimi K3.1 Pro55.1
  4. #5Claude Fable 5.153.4
artificialanalysis.ai · 2026-10-24
#10/10050.8Verified
  1. #1Claude Opus 5.557.6
  2. #9GPT-6.1 Sol51.8
  3. #10Claude Opus 550.8
  4. #11Muse Spark 1.348.1
artificialanalysis.ai · 2026-09-24

Agents benchmarks

Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.

Metric
Kimi K3.1 Pro
Claude Opus 5
τ²-bench (Telecom)
day 0
—
~#3/120~98.2%Estimated
  1. #1Step 3.7 Flash98.5%
  2. #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
  3. ~#3Claude Opus 5Estimated98.2%
  4. #3Gemini 3.1 Pro95.6%
estimated from related benchmarks
OSWorld-Verified
day 0
—
~#3/15~84.0%Estimated
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. ~#3Claude Opus 5Estimated84.0%
  4. #3Nex-N2.5-Pro82.2%
estimated from related benchmarks
OSWorld 2.0
day 0
—
~#3/5~55.3%Estimated
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Claude Opus 5Estimated55.3%
  4. #3GPT-5.6 Terra50.2%
estimated from related benchmarks
BrowseComp
day 0
—
#4/2190.8%Lab-reported
  1. #1Atria Dawn Preview92.5%
  2. #3Kimi K391.2%
  3. #4Claude Opus 590.8%
  4. #5Nex-N2.5-Pro89.7%
anthropic.com · 2026-07-24
GDPval-AA (Elo)
third-party
—
#5/901724Verified
  1. #1Claude Opus 5.51866
  2. #4Claude Fable 5.11754
  3. #5Claude Opus 51724
  4. #6Grok 4.71711
artificialanalysis.ai · 2026-10-07
AutomationBench-AA
third-party
—
#21/8356.6%Verified
  1. #1Muse Wonder Full71.3%
  2. #20DeepSeek V4 Pro (0813)56.7%
  3. #21Claude Opus 556.6%
  4. #22Qwen3.8 Max (0902)56.2%
artificialanalysis.ai · 2026-09-24
τ-Bench Banking (AA)
third-party
—
#12/9042.1%Verified
  1. #1Muse Spark 1.350.5%
  2. #11Grok 4.643.3%
  3. #12Claude Opus 542.1%
  4. #13GPT-6 Astra41.4%
artificialanalysis.ai · 2026-09-24
Not comparable across labs (1)
OSWorld 2.0 (Sept 2026 release)
day 0
—
#3/374.0%Lab-reported
  1. #1Claude Opus 5.581.8%
  2. #2Claude Fable 5.180.7%
  3. #3Claude Opus 574.0%
anthropic.com · 2026-09-22