Compare · ModelsLive · 2 picked · head to head
GPT-6.1 Sol vs Kimi K3
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-6.1 Sol wins on 22/24 benchmarks
GPT-6.1 Sol wins 22 of 24 shared benchmarks. Leads in speed · agentic · reasoning.
Category leads
speed·GPT-6.1 Solagentic·GPT-6.1 Solreasoning·GPT-6.1 Solknowledge·GPT-6.1 Solgeneral·GPT-6.1 Solcoding·GPT-6.1 Solmath·GPT-6.1 Sol
Hype vs Reality
Attention vs performance
GPT-6.1 Sol
#7 by perf·#2 by attention
Kimi K3
#67 by perf·#15 by attention
Best value
GPT-6.1 Sol
1.8x better value than Kimi K3
GPT-6.1 Sol
12.7 pts/$
$6.00/M
Kimi K3
7.1 pts/$
$8.10/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Moonshot AI
$50.0B·Tier 1
Head to head
24 benchmarks · 2 models
GPT-6.1 SolKimi K3
Artificial Analysis · CritPt
GPT-6.1 Sol leads by +8.3
GPT-6.1 Sol
31.7
Kimi K3
23.4
Artificial Analysis · GDPval
GPT-6.1 Sol leads by +3.0
GPT-6.1 Sol
54.7
Kimi K3
51.7
Artificial Analysis · Humanity's Last Exam
GPT-6.1 Sol leads by +6.0
GPT-6.1 Sol
52.9
Kimi K3
46.9
Artificial Analysis · Long Context Reasoning
Kimi K3 leads by +5.7
GPT-6.1 Sol
83.0
Kimi K3
88.7
Artificial Analysis · MMMU Pro
GPT-6.1 Sol leads by +5.5
GPT-6.1 Sol
86.0
Kimi K3
80.5
Artificial Analysis · Quality Index
GPT-6.1 Sol leads by +8.2
GPT-6.1 Sol
51.8
Kimi K3
43.6
Artificial Analysis · SciCode
Kimi K3 leads by +5.3
GPT-6.1 Sol
54.2
Kimi K3
59.5
APEX-Agents
GPT-6.1 Sol leads by +12.2
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-6.1 Sol
60.0
Kimi K3
47.8
ARC-AGI
GPT-6.1 Sol leads by +4.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-6.1 Sol
98.5
Kimi K3
94.5
ARC-AGI-2
GPT-6.1 Sol leads by +33.8
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-6.1 Sol
94.2
Kimi K3
60.4
Chess Puzzles
GPT-6.1 Sol leads by +32.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-6.1 Sol
66.3
Kimi K3
33.7
Dtbench
GPT-6.1 Sol leads by +8.9
GPT-6.1 Sol
94.2
Kimi K3
85.3
Frontiercode
GPT-6.1 Sol leads by +6.1
GPT-6.1 Sol
50.2
Kimi K3
44.2
FrontierMath-Tier-4-v2-Private
GPT-6.1 Sol leads by +61.0
GPT-6.1 Sol
100.0
Kimi K3
39.0
FrontierMath-Tiers-1-3-v2-Private
GPT-6.1 Sol leads by +22.6
GPT-6.1 Sol
98.6
Kimi K3
76.0
Furniture Assembly
GPT-6.1 Sol leads by +65.5
GPT-6.1 Sol
71.4
Kimi K3
6.0
GPQA diamond
GPT-6.1 Sol leads by +3.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-6.1 Sol
97.8
Kimi K3
94.6
Lmca
GPT-6.1 Sol leads by +11.8
GPT-6.1 Sol
73.9
Kimi K3
62.0
Mirrorcode
GPT-6.1 Sol leads by +6.7
GPT-6.1 Sol
61.1
Kimi K3
54.4
Mystery Game Puzzles
GPT-6.1 Sol leads by +59.5
GPT-6.1 Sol
78.0
Kimi K3
18.5
OTIS Mock AIME 2024-2025
GPT-6.1 Sol leads by +2.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-6.1 Sol
100.0
Kimi K3
97.2
Proofbench
GPT-6.1 Sol leads by +12.0
GPT-6.1 Sol
99.0
Kimi K3
87.0
SimpleQA Verified
GPT-6.1 Sol leads by +23.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-6.1 Sol
73.9
Kimi K3
50.6
WeirdML v3
GPT-6.1 Sol leads by +39.1
GPT-6.1 Sol
56.2
Kimi K3
17.1
Full benchmark table
| Benchmark | GPT-6.1 Sol | Kimi K3 |
|---|---|---|
Artificial Analysis · CritPt | 31.7 | 23.4 |
Artificial Analysis · GDPval | 54.7 | 51.7 |
Artificial Analysis · Humanity's Last Exam | 52.9 | 46.9 |
Artificial Analysis · Long Context Reasoning | 83.0 | 88.7 |
Artificial Analysis · MMMU Pro | 86.0 | 80.5 |
Artificial Analysis · Quality Index | 51.8 | 43.6 |
Artificial Analysis · SciCode | 54.2 | 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. | 60.0 | 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. | 94.2 | 60.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 66.3 | 33.7 |
Dtbench | 94.2 | 85.3 |
Frontiercode | 50.2 | 44.2 |
FrontierMath-Tier-4-v2-Private | 100.0 | 39.0 |
FrontierMath-Tiers-1-3-v2-Private | 98.6 | 76.0 |
Furniture Assembly | 71.4 | 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. | 97.8 | 94.6 |
Lmca | 73.9 | 62.0 |
Mirrorcode | 61.1 | 54.4 |
Mystery Game Puzzles | 78.0 | 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 |
Proofbench | 99.0 | 87.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 73.9 | 50.6 |
WeirdML v3 | 56.2 | 17.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.1M tokens (~525 books) | $40.00 | |
| $0.19 | $16.00 | 1.0M tokens (~524 books) | $41.44 |