Model comparison

Claude Opus 5.5 vs Gemini 3.1 Pro Preview

Claude Opus 5.5 is the stronger model overall, scoring 68.5 to 56.7 on the Noometry Index. Gemini 3.1 Pro Preview costs 1.8× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

Last verified October 10, 2026. 32 shared benchmarks.

Claude Opus 5.5 Anthropic

68.5

Rank #3 Confirmed

Gemini 3.1 Pro Preview

Google

56.7

Rank #20 Confirmed

Summary

They share 32 benchmarks with published results for both. Claude Opus 5.5 scores higher in 8 categories and Gemini 3.1 Pro Preview in 2 categories; 9 gaps are clear of the uncertainty.
The widest gap is in math, where Claude Opus 5.5 leads 92.4 to 61.8.
The biggest single-benchmark swing is ProofBench: 100% for Claude Opus 5.5 and 26% for Gemini 3.1 Pro Preview.
Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 5.5 and Gemini 3.1 Pro Preview specifications
	Claude Opus 5.5	Gemini 3.1 Pro Preview
Provider	Anthropic	Google
Noometry Index	68.5	56.7
Released	2026-09-22	2026-02-19
Weights	Proprietary	Proprietary
Context window	1M	1.05M
Max output	128K	66K
Input $ / M tokens	$4	$2
Output $ / M tokens	$20	$12
Results tracked	35	71

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 5.5: 71.4 (#1), Gemini 3.1 Pro Preview: 42.7 (#88)

Coding benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
LMArena WebDev	1820	1446
SciCode	66.9%	58.9%
LMArena Coding	1545	1483
MirrorCode	77.4%	8.9%
SWE-bench Verified	—	75.6%
DeepSWE	—	11.7%
FrontierCode	54.4%	—
CursorBench	57.8%	—
FrontierSWE	62.3%	—
GSO	—	22.6%
WeirdML	—	72.1%
ALE-Bench	—	1,161
AlgoTune	—	2.02

Agentic & Tool Use Claude Opus 5.5 leads

Claude Opus 5.5: 45.3 (#13), Gemini 3.1 Pro Preview: 37.7 (#33)

Agentic & Tool Use benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
APEX-Agents	73.5%	35.3%
GDP.pdf	30.6%	17%
Terminal-Bench	—	80.2%
τ²-bench Banking	—	26%
DeepResearch Bench	—	47.8%
PostTrainBench	—	22%
BALROG	—	57%
ExploitBench	—	26.1%
GBAEval	—	0.8%
LMArena Search	—	1211
METR Time Horizons	—	77%
Vending-Bench 2	—	3,774

Reasoning Claude Opus 5.5 leads

Claude Opus 5.5: 79.5 (#2), Gemini 3.1 Pro Preview: 71.7 (#9)

Reasoning benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
ARC-AGI-2	92.5%	77.1%
NYT Connections (extended)	88.5%	97.4%
ARC-AGI-1	97.5%	98%
CritPt	31.7%	17.7%
EBR-Bench	71.4%	14.3%
LMArena Hard Prompts	1545	1484
Mystery Game Puzzles	71%	34%
DTBench	98.9%	97.1%
LMCA	68.2%	53.8%
SimpleBench	—	79.6%
Chess Puzzles	—	55%
EnigmaEval	—	36.8%
Thematic Generalization	—	79.4%
Epoch Capabilities Index	—	154.92
ForecastBench	—	59

Math Claude Opus 5.5 leads

Claude Opus 5.5: 92.4 (#2), Gemini 3.1 Pro Preview: 61.8 (#28)

Math benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
FrontierMath (Tiers 1-3)	91.2%	59.6%
FrontierMath Tier 4	95%	26.8%
OTIS Mock AIME 2024-2025	100%	95.6%
ProofBench	100%	26%
MathArena Final-Answer Competitions	—	86.5%
LMArena Math	—	1485
FrontierMath (Feb 2025 set)	—	36.9%
FrontierMath Tier 4 (v1)	—	16.7%

Knowledge Gemini 3.1 Pro Preview leads

Claude Opus 5.5: 66.6 (#9), Gemini 3.1 Pro Preview: 71.8 (#3)

Knowledge benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
GPQA Diamond	90.6%	94.4%
SimpleQA Verified	72.2%	73.5%
LMArena Expert	1564	1484
Humanity's Last Exam	—	46.4%
Vectara Hallucination Rate	—	10.4%

Multimodal Claude Opus 5.5 leads

Claude Opus 5.5: 56.5 (#2), Gemini 3.1 Pro Preview: 38.1 (#60)

Multimodal benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
Furniture Assembly	83.3%	26.7%
LMArena Vision	—	1296
Blueprint-Bench 2	—	26.5%
LMArena Document	—	1444

Multilingual Claude Opus 5.5 leads

Claude Opus 5.5: 59.8 (#1), Gemini 3.1 Pro Preview: 57.1 (#11)

Multilingual benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
LMArena Non-English	1513	1475
LMArena Chinese	1572	1528
LMArena Russian	1532	1496
LMArena French	—	1488
LMArena German	—	1491
LMArena Japanese	—	1494
LMArena Korean	—	1458
LMArena Spanish	—	1480

Instruction Following Claude Opus 5.5 leads

Claude Opus 5.5: 80.1 (#2), Gemini 3.1 Pro Preview: 77.1 (#31)

Instruction Following benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
LMArena Instruction Following	1535	1465

Long Context Too close to call

Claude Opus 5.5: 47.3 (#18), Gemini 3.1 Pro Preview: 47.3 (#17)

Long Context benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
LMArena Longer Query	1540	1482
CL-bench	—	20.8%
CL-bench Life	—	16.9%

Writing & Preference Claude Opus 5.5 leads

Claude Opus 5.5: 78.7 (#3), Gemini 3.1 Pro Preview: 66.3 (#36)

Writing & Preference benchmarks
Benchmark	Claude Opus 5.5	Gemini 3.1 Pro Preview
LMArena Text	1518	1480
LMArena Creative Writing	1538	1482
EQ-Bench Creative Writing	2050	1491
LMArena Multi-Turn	1520	1486
EQ-Bench 4	—	1142

Frequently asked questions

Is Claude Opus 5.5 better than Gemini 3.1 Pro Preview?

Which is cheaper, Claude Opus 5.5 or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

Is Claude Opus 5.5 or Gemini 3.1 Pro Preview better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.4 versus 42.7 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 5.5 and Gemini 3.1 Pro Preview share?

32 benchmarks have published results for both models. Claude Opus 5.5 has 35 scored results on Noometry and Gemini 3.1 Pro Preview has 71.