Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5.5 vs GPT-6.1 Sol
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-6.1 Sol wins on 13/25 benchmarks
GPT-6.1 Sol wins 13 of 25 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
speed·Claude Sonnet 5.5agentic·Claude Sonnet 5.5reasoning·GPT-6.1 Solknowledge·GPT-6.1 Solgeneral·Claude Sonnet 5.5coding·Claude Sonnet 5.5math·GPT-6.1 Sol
Head to head · from the data · data as of 2026-11-22
- Benchmarks · Claude Sonnet 5.5 leads on 11 of 25 shared benchmarks (Artificial Analysis · GDPval, Artificial Analysis · Humanity's Last Exam, Artificial Analysis · Quality Index, Artificial Analysis · SciCode, 7 more), GPT-6.1 Sol on 13 (Artificial Analysis · CritPt, Artificial Analysis · Long Context Reasoning, ARC-AGI, ARC-AGI-2, 9 more) · 1 tied
- Price · Claude Sonnet 5.5 input $2.00/M vs GPT-6.1 Sol $2.00/M, the same input price (OpenRouter list price, as of 2026-11-22)
- Cheapest provider · Claude Sonnet 5.5 at Amazon Bedrock and 4 other providers $2.00/M input (of 5 offers) as of 2026-11-22 · GPT-6.1 Sol at OpenAI $1.00/M input (of 6 offers) as of 2026-11-22
- Context · Claude Sonnet 5.5 1.0M tokens vs GPT-6.1 Sol 1.1M tokens
- Released · Claude Sonnet 5.5 Sep 28, 2026 vs GPT-6.1 Sol Sep 29, 2026 · the same month
- Gecko tests · Censorship Index: Claude Sonnet 5.5 refuses or dodges 0% vs GPT-6.1 Sol 2.5% · Knowledge Horizon: Claude Sonnet 5.5 knows news up to May 2026 vs GPT-6.1 Sol Mar 2026
- Price history · Claude Sonnet 5.5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22 · GPT-6.1 Sol OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-22
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Claude Sonnet 5.5
#19 by perf·#14 by attention
GPT-6.1 Sol
#11 by perf·#2 by attention
Best value
GPT-6.1 Sol
1.0x better value than Claude Sonnet 5.5
Claude Sonnet 5.5
11.9 pts/$
$6.00/M
GPT-6.1 Sol
12.5 pts/$
$6.00/M
Vendor risk
Who is behind the model
Anthropic
$1.40T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
25 benchmarks · 2 models
Claude Sonnet 5.5GPT-6.1 Sol
Artificial Analysis · CritPt
GPT-6.1 Sol leads by +0.3
Claude Sonnet 5.5
31.4
GPT-6.1 Sol
31.7
Artificial Analysis · GDPval
Claude Sonnet 5.5 leads by +12.2
Claude Sonnet 5.5
66.9
GPT-6.1 Sol
54.7
Artificial Analysis · Humanity's Last Exam
Claude Sonnet 5.5 leads by +2.1
Claude Sonnet 5.5
55.0
GPT-6.1 Sol
52.9
Artificial Analysis · Long Context Reasoning
GPT-6.1 Sol leads by +0.3
Claude Sonnet 5.5
82.7
GPT-6.1 Sol
83.0
Artificial Analysis · Quality Index
Claude Sonnet 5.5 leads by +4.2
Claude Sonnet 5.5
56.0
GPT-6.1 Sol
51.8
Artificial Analysis · SciCode
Claude Sonnet 5.5 leads by +6.8
Claude Sonnet 5.5
61.0
GPT-6.1 Sol
54.2
APEX-Agents
Claude Sonnet 5.5 leads by +15.5
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Sonnet 5.5
75.5
GPT-6.1 Sol
60.0
ARC-AGI
GPT-6.1 Sol leads by +2.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Sonnet 5.5
96.5
GPT-6.1 Sol
98.5
ARC-AGI-2
GPT-6.1 Sol leads by +10.3
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Sonnet 5.5
83.9
GPT-6.1 Sol
94.2
Chess Puzzles
GPT-6.1 Sol leads by +9.5
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Sonnet 5.5
56.9
GPT-6.1 Sol
66.3
Dtbench
Claude Sonnet 5.5 leads by +1.3
Claude Sonnet 5.5
95.5
GPT-6.1 Sol
94.2
Frontiercode
Claude Sonnet 5.5 leads by +1.9
Claude Sonnet 5.5
52.1
GPT-6.1 Sol
50.2
FrontierMath-Tier-4-v2-Private
GPT-6.1 Sol leads by +19.5
Claude Sonnet 5.5
80.5
GPT-6.1 Sol
100.0
FrontierMath-Tiers-1-3-v2-Private
GPT-6.1 Sol leads by +5.2
Claude Sonnet 5.5
93.4
GPT-6.1 Sol
98.6
Furniture Assembly
GPT-6.1 Sol leads by +7.1
Claude Sonnet 5.5
64.3
GPT-6.1 Sol
71.4
GPQA diamond
Claude Sonnet 5.5 leads by +0.3
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Sonnet 5.5
98.0
GPT-6.1 Sol
97.8
Lmca
Claude Sonnet 5.5 leads by +6.5
Claude Sonnet 5.5
80.3
GPT-6.1 Sol
73.9
Mirrorcode
Claude Sonnet 5.5 leads by +36.7
Claude Sonnet 5.5
97.8
GPT-6.1 Sol
61.1
Mystery Game Puzzles
GPT-6.1 Sol leads by +16.5
Claude Sonnet 5.5
61.5
GPT-6.1 Sol
78.0
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Sonnet 5.5
100.0
GPT-6.1 Sol
100.0
Proofbench
Claude Sonnet 5.5 leads by +1.0
Claude Sonnet 5.5
100.0
GPT-6.1 Sol
99.0
SimpleBench
GPT-6.1 Sol leads by +8.4
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Sonnet 5.5
71.1
GPT-6.1 Sol
79.5
SimpleQA Verified
GPT-6.1 Sol leads by +27.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Sonnet 5.5
46.5
GPT-6.1 Sol
73.9
SpireClimb
GPT-6.1 Sol leads by +22.5
Claude Sonnet 5.5
1.3
GPT-6.1 Sol
23.8
WeirdML v3
GPT-6.1 Sol leads by +15.1
Claude Sonnet 5.5
41.1
GPT-6.1 Sol
56.2
Full benchmark table
| Benchmark | Claude Sonnet 5.5 | GPT-6.1 Sol |
|---|---|---|
Artificial Analysis · CritPt | 31.4 | 31.7 |
Artificial Analysis · GDPval | 66.9 | 54.7 |
Artificial Analysis · Humanity's Last Exam | 55.0 | 52.9 |
Artificial Analysis · Long Context Reasoning | 82.7 | 83.0 |
Artificial Analysis · Quality Index | 56.0 | 51.8 |
Artificial Analysis · SciCode | 61.0 | 54.2 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 75.5 | 60.0 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 96.5 | 98.5 |
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. | 83.9 | 94.2 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 56.9 | 66.3 |
Dtbench | 95.5 | 94.2 |
Frontiercode | 52.1 | 50.2 |
FrontierMath-Tier-4-v2-Private | 80.5 | 100.0 |
FrontierMath-Tiers-1-3-v2-Private | 93.4 | 98.6 |
Furniture Assembly | 64.3 | 71.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 98.0 | 97.8 |
Lmca | 80.3 | 73.9 |
Mirrorcode | 97.8 | 61.1 |
Mystery Game Puzzles | 61.5 | 78.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 100.0 |
Proofbench | 100.0 | 99.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 71.1 | 79.5 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 46.5 | 73.9 |
SpireClimb | 1.3 | 23.8 |
WeirdML v3 | 41.1 | 56.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 | |
| $2.00 | $10.00 | 1.1M tokens (~525 books) | $40.00 |
Claude Sonnet 5.5 vs GPT-6.1 Sol · questions answered from the data
Claude Sonnet 5.5 leads on 11 of 25 shared benchmarks (Artificial Analysis · GDPval, Artificial Analysis · Humanity's Last Exam, Artificial Analysis · Quality Index, Artificial Analysis · SciCode, 7 more), GPT-6.1 Sol on 13 (Artificial Analysis · CritPt, Artificial Analysis · Long Context Reasoning, ARC-AGI, ARC-AGI-2, 9 more) · 1 tied