Compare · ModelsLive · 2 picked · head to head
Claude Sonnet 5.5 vs Gemini 4 Argon
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Sonnet 5.5 wins on 13/18 benchmarks
Claude Sonnet 5.5 wins 13 of 18 shared benchmarks. Leads in speed · coding · math.
Category leads
speed·Claude Sonnet 5.5agentic·Gemini 4 Argonknowledge·Gemini 4 Argoncoding·Claude Sonnet 5.5math·Claude Sonnet 5.5general·Claude Sonnet 5.5
Hype vs Reality
Attention vs performance
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 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
Google DeepMind
$4.27T·Tier 1
Head to head
18 benchmarks · 2 models
Claude Sonnet 5.5Gemini 4 Argon
Artificial Analysis · CritPt
Claude Sonnet 5.5 leads by +4.3
Claude Sonnet 5.5
31.4
Gemini 4 Argon
27.1
Artificial Analysis · GDPval
Claude Sonnet 5.5 leads by +10.7
Claude Sonnet 5.5
66.9
Gemini 4 Argon
56.2
Artificial Analysis · Humanity's Last Exam
Gemini 4 Argon leads by +2.1
Claude Sonnet 5.5
55.0
Gemini 4 Argon
57.1
Artificial Analysis · Long Context Reasoning
Claude Sonnet 5.5 leads by +3.0
Claude Sonnet 5.5
82.7
Gemini 4 Argon
79.7
Artificial Analysis · Quality Index
Claude Sonnet 5.5 leads by +3.4
Claude Sonnet 5.5
56.0
Gemini 4 Argon
52.6
Artificial Analysis · SciCode
Gemini 4 Argon leads by +0.8
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 Sonnet 5.5
75.5
Gemini 4 Argon
82.4
Chess Puzzles
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
Gemini 4 Argon
56.9
Frontiercode
Claude Sonnet 5.5 leads by +4.5
Claude Sonnet 5.5
52.1
Gemini 4 Argon
47.5
FrontierMath-Tier-4-v2-Private
Claude Sonnet 5.5 leads by +2.4
Claude Sonnet 5.5
80.5
Gemini 4 Argon
78.0
FrontierMath-Tiers-1-3-v2-Private
Claude Sonnet 5.5 leads by +2.8
Claude Sonnet 5.5
88.8
Gemini 4 Argon
86.0
Frontierswe
Claude Sonnet 5.5 leads by +6.9
Claude Sonnet 5.5
61.9
Gemini 4 Argon
55.0
Furniture Assembly
Claude Sonnet 5.5 leads by +3.6
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 Sonnet 5.5
94.1
Gemini 4 Argon
95.2
Mystery Game Puzzles
Claude Sonnet 5.5 leads by +1.1
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 Sonnet 5.5
100.0
Gemini 4 Argon
100.0
Proofbench
Claude Sonnet 5.5 leads by +1.0
Claude Sonnet 5.5
100.0
Gemini 4 Argon
99.0
SimpleQA Verified
Gemini 4 Argon leads by +29.5
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
Gemini 4 Argon
76.0
Full benchmark table
| Benchmark | Claude Sonnet 5.5 | Gemini 4 Argon |
|---|---|---|
Artificial Analysis · CritPt | 31.4 | 27.1 |
Artificial Analysis · GDPval | 66.9 | 56.2 |
Artificial Analysis · Humanity's Last Exam | 55.0 | 57.1 |
Artificial Analysis · Long Context Reasoning | 82.7 | 79.7 |
Artificial Analysis · Quality Index | 56.0 | 52.6 |
Artificial Analysis · SciCode | 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. | 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. | 56.9 | 56.9 |
Frontiercode | 52.1 | 47.5 |
FrontierMath-Tier-4-v2-Private | 80.5 | 78.0 |
FrontierMath-Tiers-1-3-v2-Private | 88.8 | 86.0 |
Frontierswe | 61.9 | 55.0 |
Furniture Assembly | 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. | 94.1 | 95.2 |
Mystery Game Puzzles | 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 |
Proofbench | 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. | 46.5 | 76.0 |
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 | 1.0M tokens (~524 books) | $40.00 |