Compare · ModelsLive · 3 picked · head to head
Claude Opus 5.5 vs Claude Sonnet 5.5 vs Gemini 4 Argon
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Opus 5.5 wins on 16/19 benchmarks
Claude Opus 5.5 wins 16 of 19 shared benchmarks. Leads in speed · knowledge · coding.
Category leads
speed·Claude Opus 5.5agentic·Gemini 4 Argonknowledge·Claude Opus 5.5coding·Claude Opus 5.5math·Claude Opus 5.5general·Claude Opus 5.5
Hype vs Reality
Attention vs performance
Claude Opus 5.5
#12 by perf·#9 by attention
Claude Sonnet 5.5
#34 by perf·#12 by attention
Gemini 4 Argon
#11 by perf·#1 by attention
Best value
Gemini 4 Argon
1.1x better value than Claude Sonnet 5.5
Claude Opus 5.5
6.2 pts/$
$12.00/M
Claude Sonnet 5.5
11.0 pts/$
$6.00/M
Gemini 4 Argon
12.5 pts/$
$6.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Google DeepMind
$4.27T·Tier 1
Head to head
19 benchmarks · 3 models
Claude Opus 5.5Claude Sonnet 5.5Gemini 4 Argon
Artificial Analysis · CritPt
Claude Opus 5.5 leads by +0.3
Claude Opus 5.5
31.7
Claude Sonnet 5.5
31.4
Gemini 4 Argon
27.1
Artificial Analysis · GDPval
Claude Opus 5.5 leads by +1.4
Claude Opus 5.5
68.3
Claude Sonnet 5.5
66.9
Gemini 4 Argon
56.2
Artificial Analysis · Humanity's Last Exam
Claude Opus 5.5 leads by +4.3
Claude Opus 5.5
61.4
Claude Sonnet 5.5
55.0
Gemini 4 Argon
57.1
Artificial Analysis · Long Context Reasoning
Claude Opus 5.5 leads by +2.0
Claude Opus 5.5
84.7
Claude Sonnet 5.5
82.7
Gemini 4 Argon
79.7
Artificial Analysis · Quality Index
Claude Opus 5.5 leads by +1.6
Claude Opus 5.5
57.6
Claude Sonnet 5.5
56.0
Gemini 4 Argon
52.6
Artificial Analysis · SciCode
Claude Opus 5.5 leads by +5.1
Claude Opus 5.5
66.9
Claude Sonnet 5.5
61.0
Gemini 4 Argon
61.8
APEX-Agents
Gemini 4 Argon leads by +6.9
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
Claude Sonnet 5.5
75.5
Gemini 4 Argon
82.4
Chess Puzzles
Claude Opus 5.5 leads by +8.4
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
Claude Sonnet 5.5
56.9
Gemini 4 Argon
56.9
Frontiercode
Claude Opus 5.5 leads by +2.5
Claude Opus 5.5
54.6
Claude Sonnet 5.5
52.1
Gemini 4 Argon
47.5
FrontierMath-Tier-4-v2-Private
Claude Opus 5.5 leads by +14.5
Claude Opus 5.5
95.0
Claude Sonnet 5.5
80.5
Gemini 4 Argon
78.0
FrontierMath-Tiers-1-3-v2-Private
Claude Opus 5.5 leads by +2.5
Claude Opus 5.5
91.2
Claude Sonnet 5.5
88.8
Gemini 4 Argon
86.0
Frontierswe
Claude Opus 5.5 leads by +0.4
Claude Opus 5.5
62.3
Claude Sonnet 5.5
61.9
Gemini 4 Argon
55.0
Furniture Assembly
Claude Opus 5.5 leads by +11.9
Claude Opus 5.5
76.2
Claude Sonnet 5.5
64.3
Gemini 4 Argon
60.7
GPQA diamond
Gemini 4 Argon leads by +1.1
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
87.5
Claude Sonnet 5.5
94.1
Gemini 4 Argon
95.2
Mystery Game Puzzles
Claude Opus 5.5 leads by +6.6
Claude Opus 5.5
68.0
Claude Sonnet 5.5
61.5
Gemini 4 Argon
60.3
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Opus 5.5
100.0
Claude Sonnet 5.5
100.0
Gemini 4 Argon
100.0
Proofbench
Claude Opus 5.5
100.0
Claude Sonnet 5.5
100.0
Gemini 4 Argon
99.0
SimpleQA Verified
Gemini 4 Argon leads by +3.8
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
Claude Sonnet 5.5
46.5
Gemini 4 Argon
76.0
SpireClimb
Claude Opus 5.5 leads by +2.0
Claude Opus 5.5
3.3
Claude Sonnet 5.5
1.3
Full benchmark table
| Benchmark | Claude Opus 5.5 | Claude Sonnet 5.5 | Gemini 4 Argon |
|---|---|---|---|
Artificial Analysis · CritPt | 31.7 | 31.4 | 27.1 |
Artificial Analysis · GDPval | 68.3 | 66.9 | 56.2 |
Artificial Analysis · Humanity's Last Exam | 61.4 | 55.0 | 57.1 |
Artificial Analysis · Long Context Reasoning | 84.7 | 82.7 | 79.7 |
Artificial Analysis · Quality Index | 57.6 | 56.0 | 52.6 |
Artificial Analysis · SciCode | 66.9 | 61.0 | 61.8 |
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 | 75.5 | 82.4 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 65.3 | 56.9 | 56.9 |
Frontiercode | 54.6 | 52.1 | 47.5 |
FrontierMath-Tier-4-v2-Private | 95.0 | 80.5 | 78.0 |
FrontierMath-Tiers-1-3-v2-Private | 91.2 | 88.8 | 86.0 |
Frontierswe | 62.3 | 61.9 | 55.0 |
Furniture Assembly | 76.2 | 64.3 | 60.7 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 87.5 | 94.1 | 95.2 |
Mystery Game Puzzles | 68.0 | 61.5 | 60.3 |
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 | 100.0 |
Proofbench | 100.0 | 100.0 | 99.0 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 72.2 | 46.5 | 76.0 |
SpireClimb | 3.3 | 1.3 | — |
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 | |
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 | |
| $2.00 | $10.00 | 1.0M tokens (~524 books) | $40.00 |