Compare · ModelsLive · 2 picked · head to head

Claude Opus 5.5 vs Gemini 3.8 Flash

Side by side · benchmarks, pricing, and signals you can act on.

CiteAdd another

Winner summary

Claude Opus 5.5 wins on 23/24 benchmarks

Claude Opus 5.5 wins 23 of 24 shared benchmarks. Leads in speed · agentic · reasoning.

Category leads

speed·Claude Opus 5.5agentic·Claude Opus 5.5reasoning·Claude Opus 5.5knowledge·Claude Opus 5.5general·Claude Opus 5.5coding·Claude Opus 5.5math·Claude Opus 5.5

Hype vs Reality

Attention vs performance

Claude Opus 5.5

#12 by perf·#9 by attention

DESERVED

Gemini 3.8 Flash

#53 by perf·#6 by attention

DESERVED

See full mindshare →

Best value

Gemini 3.8 Flash

4.3x better value than Claude Opus 5.5

Claude Opus 5.5

6.2 pts/$

$12.00/M

Gemini 3.8 Flash

26.5 pts/$

$2.25/M

Explore pricing →

Vendor risk

Who is behind the model

Anthropic

$965.0B·Tier 1

Medium risk

Google DeepMind

$4.27T·Tier 1

Low risk

See the AI economy →

Head to head

24 benchmarks · 2 models

Claude Opus 5.5Gemini 3.8 Flash

Artificial Analysis · CritPt

Claude Opus 5.5 leads by +13.4

Claude Opus 5.5

31.7

Gemini 3.8 Flash

18.3

Artificial Analysis · GDPval

Claude Opus 5.5 leads by +21.5

Claude Opus 5.5

68.3

Gemini 3.8 Flash

46.8

Artificial Analysis · Humanity's Last Exam

Claude Opus 5.5 leads by +13.6

Claude Opus 5.5

61.4

Gemini 3.8 Flash

47.8

Artificial Analysis · Long Context Reasoning

Claude Opus 5.5 leads by +3.4

Claude Opus 5.5

84.7

Gemini 3.8 Flash

81.3

Artificial Analysis · MMMU Pro

Claude Opus 5.5 leads by +2.1

Claude Opus 5.5

87.7

Gemini 3.8 Flash

85.6

Artificial Analysis · Quality Index

Claude Opus 5.5 leads by +16.7

Claude Opus 5.5

57.6

Gemini 3.8 Flash

40.9

Artificial Analysis · SciCode

Claude Opus 5.5 leads by +10.3

Claude Opus 5.5

66.9

Gemini 3.8 Flash

56.6

APEX-Agents

Claude Opus 5.5 leads by +9.2

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

Gemini 3.8 Flash

64.3

ARC-AGI

ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.

Claude Opus 5.5

98.5

Gemini 3.8 Flash

98.5

ARC-AGI-2

Claude Opus 5.5 leads by +4.2

ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.

Claude Opus 5.5

93.3

Gemini 3.8 Flash

89.2

Chess Puzzles

Claude Opus 5.5 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 Opus 5.5

65.3

Gemini 3.8 Flash

55.8

Dtbench

Claude Opus 5.5 leads by +5.3

Claude Opus 5.5

98.2

Gemini 3.8 Flash

92.9

Frontiercode

Claude Opus 5.5 leads by +13.5

Claude Opus 5.5

54.6

Gemini 3.8 Flash

41.2

FrontierMath-Tier-4-v2-Private

Claude Opus 5.5 leads by +73.0

Claude Opus 5.5

95.0

Gemini 3.8 Flash

21.9

FrontierMath-Tiers-1-3-v2-Private

Claude Opus 5.5 leads by +22.8

Claude Opus 5.5

91.2

Gemini 3.8 Flash

68.4

Frontierswe

Claude Opus 5.5 leads by +42.7

Claude Opus 5.5

62.3

Gemini 3.8 Flash

19.6

Furniture Assembly

Claude Opus 5.5 leads by +73.8

Claude Opus 5.5

76.2

Gemini 3.8 Flash

2.4

GPQA diamond

Gemini 3.8 Flash leads by +6.4

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

Gemini 3.8 Flash

93.9

Lmca

Claude Opus 5.5 leads by +18.0

Claude Opus 5.5

80.3

Gemini 3.8 Flash

62.2

Mystery Game Puzzles

Claude Opus 5.5 leads by +26.4

Claude Opus 5.5

68.0

Gemini 3.8 Flash

41.6

OTIS Mock AIME 2024-2025

Claude Opus 5.5 leads by +1.1

OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.

Claude Opus 5.5

100.0

Gemini 3.8 Flash

98.9

Proofbench

Claude Opus 5.5 leads by +52.0

Claude Opus 5.5

100.0

Gemini 3.8 Flash

48.0

Remote Labor Index

Claude Opus 5.5 leads by +15.4

Claude Opus 5.5

21.3

Gemini 3.8 Flash

5.8

SimpleQA Verified

Claude Opus 5.5 leads by +2.5

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

Gemini 3.8 Flash

69.7

Full benchmark table

Benchmark	Claude Opus 5.5	Gemini 3.8 Flash
Artificial Analysis · CritPt	31.7	18.3
Artificial Analysis · GDPval	68.3	46.8
Artificial Analysis · Humanity's Last Exam	61.4	47.8
Artificial Analysis · Long Context Reasoning	84.7	81.3
Artificial Analysis · MMMU Pro	87.7	85.6
Artificial Analysis · Quality Index	57.6	40.9
Artificial Analysis · SciCode	66.9	56.6
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	64.3
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.	98.5	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.	93.3	89.2
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.	65.3	55.8
Dtbench	98.2	92.9
Frontiercode	54.6	41.2
FrontierMath-Tier-4-v2-Private	95.0	21.9
FrontierMath-Tiers-1-3-v2-Private	91.2	68.4
Frontierswe	62.3	19.6
Furniture Assembly	76.2	2.4
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.	87.5	93.9
Lmca	80.3	62.2
Mystery Game Puzzles	68.0	41.6
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.	100.0	98.9
Proofbench	100.0	48.0
Remote Labor Index	21.3	5.8
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.	72.2	69.7

Pricing · per 1M tokens · projected $/mo at 10M tokens

Model	Input	Output	Context	Projected $/mo
Claude Opus 5.5	$4.00	$20.00	1.0M tokens (~500 books)	$80.00
Gemini 3.8 Flash	$0.75	$3.75	1.0M tokens (~524 books)	$15.00

People also compared

Claude Opus 5.5 vs GPT-5.5 Pro Claude Opus 5.5 vs GPT-5.5 Claude Opus 5.5 vs GPT-5 Chat Claude Mythos Preview vs Claude Opus 5.5 Claude Opus 5.5 vs DeepSeek V3.2 Speciale Claude Opus 5.5 vs GPT-6.1 Sol Claude Opus 5.5 vs Step 3.5 Flash Claude Opus 5.5 vs DeepSeek-V2 (MoE-236B, May 2024)