Gemini 4 Argon vs Claude Sonnet 5.5
Wins 2 of 6 areas
Reasoning · Facts
Wins 4 of 6 areas
Coding · Agents · Math · Long documents
Claude Sonnet 5.5 is the stronger all-rounder.Gemini 4 Argon is better at reasoning.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- AgentsCarrying out multi-step tasks on its own02Claude Sonnet 5.52 of 2 tests
- MathCompetition and research-level math02Claude Sonnet 5.52 of 2 tests
- CodingWriting and fixing software01Claude Sonnet 5.51 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Claude Sonnet 5.51 of 1 test
- ReasoningHard problems that need careful thinking31Gemini 4 Argon3 of 4 tests
- FactsGetting facts right instead of making them up21Gemini 4 Argon2 of 3 tests
Long documents rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 5.5 pulls ahead
Where Gemini 4 Argon pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+31.9points ahead
- Short factual questions, answered correctlySimpleQA Verified+29.5points ahead
- Solves new puzzle games it has never seenARC-AGI-3+22points ahead
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 5.5
- LMArena · WebDevClaude Sonnet 5.5 by 91 rating points16831774+91 rating
- SciCodetie61.861tie
AgentsClaude Sonnet 5.5
- GDPValClaude Sonnet 5.5 by 10.756.266.9+10.7
- Terminal-Bench 4.0Claude Sonnet 5.5 by 6.557.163.6+6.5
ReasoningGemini 4 Argon
- ARC-AGI-3Gemini 4 Argon by 2246.324.3+22
- ARC-AGI-2Gemini 4 Argon by 7.491.383.9+7.4
- CritPtClaude Sonnet 5.5 by 4.327.131.4+4.3
- Humanity's Last ExamGemini 4 Argon by 2.157.155+2.1
FactsGemini 4 Argon
- AA-Omniscience · Non-hallucinationGemini 4 Argon by 31.984.953+31.9
- SimpleQA VerifiedGemini 4 Argon by 29.57646.5+29.5
- AA-Omniscience · AccuracyClaude Sonnet 5.5 by 4.149.954+4.1
MathClaude Sonnet 5.5
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 5.5 by 2.88688.8+2.8
- FrontierMath Tier 4Claude Sonnet 5.5 by 2.47880.5+2.4
Other results11 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- Terminal-Bench 4.0Claude Sonnet 5.5 by 13.257.470.6+13.2
- HealthBenchClaude Sonnet 5.5 by 1349.162.1+13
- AA-OmniscienceGemini 4 Argon by 10.142.432.3+10.1
- HealthBench ProfessionalClaude Sonnet 5.5 by 7.955.163+7.9
- DeepSWE 1.1Gemini 4 Argon by 6.977.971+6.9
- CritPt v2 HardClaude Sonnet 5.5 by 6.552.559+6.5
- GDP (Surge AI)Claude Sonnet 5.5 by 421.825.8+4
- AA IntelligenceClaude Sonnet 5.5 by 3.452.656+3.4
- HLE-DiamondGemini 4 Argon by 3.456.753.3+3.4
- ARC-AGI-1Gemini 4 Argon by 298.596.5+2
- Terminal-Bench-Science 0.1tie52.953.3tie
Questions people ask
Which is better, Gemini 4 Argon or Claude Sonnet 5.5?
Claude Sonnet 5.5 wins four of the six areas where both have results: coding, agents, math and long documents. Gemini 4 Argon wins reasoning and facts.
Which is better for coding?
Claude Sonnet 5.5. It wins 1 of the 2 coding tests both models report; Gemini 4 Argon wins none, and 1 is a tie.
Which is cheaper?
Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.