Compare · ModelsLive · 2 picked · head to head
Claude Opus 5.5 vs Kimi K3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 5.5 wins on 26/27 benchmarks
Claude Opus 5.5 wins 26 of 27 shared benchmarks. Leads in speed · agentic · reasoning.
Category leads
speed·Claude Opus 5.5agentic·Claude Opus 5.5reasoning·Claude Opus 5.5knowledge·Claude Opus 5.5general·Claude Opus 5.5coding·Claude Opus 5.5math·Claude Opus 5.5
Head to head · from the data · data as of 2026-11-22
- Benchmarks · Claude Opus 5.5 leads on 26 of 27 shared benchmarks (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · Humanity's Last Exam, Artificial Analysis · MMMU Pro, 22 more), Kimi K3 on 1 (Artificial Analysis · Long Context Reasoning)
- Price · Claude Opus 5.5 input $4.00/M vs Kimi K3 $0.19/M, Kimi K3 is 95% cheaper (OpenRouter list price, as of 2026-11-22)
- Cheapest provider · Claude Opus 5.5 at Amazon Bedrock and 4 other providers $4.00/M input (of 6 offers) as of 2026-11-22 · Kimi K3 at Wafer $0.15/M input (of 29 offers) as of 2026-11-22
- Context · Claude Opus 5.5 1.0M tokens vs Kimi K3 1.0M tokens
- Released · Claude Opus 5.5 Sep 22, 2026 vs Kimi K3 Jul 16, 2026 · 2 months apart
- Gecko tests · Knowledge Horizon: Claude Opus 5.5 knows news up to May 2026 vs Kimi K3 Nov 2025
- Price history · Claude Opus 5.5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Claude Opus 5.5
#12 by perf·#5 by attention
Kimi K3
#72 by perf·#16 by attention
Best value
Kimi K3
1.1x better value than Claude Opus 5.5
Claude Opus 5.5
6.2 pts/$
$12.00/M
Kimi K3
7.1 pts/$
$8.10/M
Vendor risk
Who is behind the model
Anthropic
$1.40T·Tier 1
Moonshot AI
$50.0B·Tier 1
Head to head
27 benchmarks · 2 models
Claude Opus 5.5Kimi K3
Artificial Analysis · CritPt
Claude Opus 5.5 leads by +8.3
Claude Opus 5.5
31.7
Kimi K3
23.4
Artificial Analysis · GDPval
Claude Opus 5.5 leads by +16.6
Claude Opus 5.5
68.3
Kimi K3
51.7
Artificial Analysis · Humanity's Last Exam
Claude Opus 5.5 leads by +14.5
Claude Opus 5.5
61.4
Kimi K3
46.9
Artificial Analysis · Long Context Reasoning
Kimi K3 leads by +4.0
Claude Opus 5.5
84.7
Kimi K3
88.7
Artificial Analysis · MMMU Pro
Claude Opus 5.5 leads by +7.2
Claude Opus 5.5
87.7
Kimi K3
80.5
Artificial Analysis · Quality Index
Claude Opus 5.5 leads by +14.0
Claude Opus 5.5
57.6
Kimi K3
43.6
Artificial Analysis · SciCode
Claude Opus 5.5 leads by +7.4
Claude Opus 5.5
66.9
Kimi K3
59.5
APEX-Agents
Claude Opus 5.5 leads by +25.7
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Opus 5.5
73.5
Kimi K3
47.8
ARC-AGI
Claude Opus 5.5 leads by +4.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Opus 5.5
98.5
Kimi K3
94.5
ARC-AGI-2
Claude Opus 5.5 leads by +32.9
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Opus 5.5
93.3
Kimi K3
60.4
Chess Puzzles
Claude Opus 5.5 leads by +31.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Opus 5.5
65.3
Kimi K3
33.7
Dtbench
Claude Opus 5.5 leads by +12.9
Claude Opus 5.5
98.2
Kimi K3
85.3
Frontiercode
Claude Opus 5.5 leads by +10.5
Claude Opus 5.5
54.6
Kimi K3
44.2
FrontierMath-Tier-4-v2-Private
Claude Opus 5.5 leads by +56.0
Claude Opus 5.5
95.0
Kimi K3
39.0
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 5.5 leads by +20.0
Claude Opus 5.5
96.0
Kimi K3
76.0
Frontierswe
Claude Opus 5.5 leads by +36.5
Claude Opus 5.5
62.3
Kimi K3
25.9
Furniture Assembly
Claude Opus 5.5 leads by +70.2
Claude Opus 5.5
76.2
Kimi K3
6.0
GPQA diamond
Claude Opus 5.5 leads by +1.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Opus 5.5
95.9
Kimi K3
94.6
Lmca
Claude Opus 5.5 leads by +18.2
Claude Opus 5.5
80.3
Kimi K3
62.0
Mirrorcode
Claude Opus 5.5 leads by +41.1
Claude Opus 5.5
95.6
Kimi K3
54.4
Mystery Game Puzzles
Claude Opus 5.5 leads by +49.6
Claude Opus 5.5
68.0
Kimi K3
18.5
OTIS Mock AIME 2024-2025
Claude Opus 5.5 leads by +2.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 5.5
100.0
Kimi K3
97.2
PostTrainBench
Claude Opus 5.5 leads by +12.3
Claude Opus 5.5
43.8
Kimi K3
31.5
Proofbench
Claude Opus 5.5 leads by +13.0
Claude Opus 5.5
100.0
Kimi K3
87.0
SimpleBench
Claude Opus 5.5 leads by +33.2
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Opus 5.5
86.1
Kimi K3
52.8
SimpleQA Verified
Claude Opus 5.5 leads by +21.6
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Opus 5.5
72.2
Kimi K3
50.6
WeirdML v3
Claude Opus 5.5 leads by +38.3
Claude Opus 5.5
55.4
Kimi K3
17.1
Full benchmark table
| Benchmark | Claude Opus 5.5 | Kimi K3 |
|---|---|---|
Artificial Analysis · CritPt | 31.7 | 23.4 |
Artificial Analysis · GDPval | 68.3 | 51.7 |
Artificial Analysis · Humanity's Last Exam | 61.4 | 46.9 |
Artificial Analysis · Long Context Reasoning | 84.7 | 88.7 |
Artificial Analysis · MMMU Pro | 87.7 | 80.5 |
Artificial Analysis · Quality Index | 57.6 | 43.6 |
Artificial Analysis · SciCode | 66.9 | 59.5 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 73.5 | 47.8 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 98.5 | 94.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 93.3 | 60.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 65.3 | 33.7 |
Dtbench | 98.2 | 85.3 |
Frontiercode | 54.6 | 44.2 |
FrontierMath-Tier-4-v2-Private | 95.0 | 39.0 |
FrontierMath-Tiers-1-3-v2-Private | 96.0 | 76.0 |
Frontierswe | 62.3 | 25.9 |
Furniture Assembly | 76.2 | 6.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 95.9 | 94.6 |
Lmca | 80.3 | 62.0 |
Mirrorcode | 95.6 | 54.4 |
Mystery Game Puzzles | 68.0 | 18.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 97.2 |
PostTrainBench | 43.8 | 31.5 |
Proofbench | 100.0 | 87.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 86.1 | 52.8 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 72.2 | 50.6 |
WeirdML v3 | 55.4 | 17.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $4.00 | $20.00 | 1.0M tokens (~500 books) | $80.00 | |
| $0.19 | $16.00 | 1.0M tokens (~524 books) | $41.44 |
Claude Opus 5.5 vs Kimi K3 · questions answered from the data
Claude Opus 5.5 leads on 26 of 27 shared benchmarks (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · Humanity's Last Exam, Artificial Analysis · MMMU Pro, 22 more), Kimi K3 on 1 (Artificial Analysis · Long Context Reasoning)
People also compared