Multimodal
Like-for-like- Claude Opus 4.5
- 69.9
- Gemini 3.1 Pro
- 82.6
- Weighted basis
- 2 vs 2 rows
- Reading
- Gemini 3.1 Pro leads
Claude Opus 4.5 vs Gemini 3.1 Pro
Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Opus 4.5 has the higher public score estimate, 63.6 versus 56.49, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
7 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Long documents
Prompts that approach the documented context limit
Gemini 3.1 Pro
Gemini 3.1 Pro has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Gemini 3.1 Pro
Gemini 3.1 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Gemini 3.1 Pro
Gemini 3.1 Pro has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
38 Claude Opus 4.5 only
7 Shared
16 Gemini 3.1 Pro only
- Shared results
- 7
- Claude Opus 4.5 only
- 38
- Gemini 3.1 Pro only
- 16
- Like-for-like categories
- 1 / 8
1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Math
Directional only- Claude Opus 4.5
- 57.5
- Gemini 3.1 Pro
- 31.8
- Weighted basis
- 4 vs 2 rows
- Reading
- Directional only
Agentic
Not comparable- Claude Opus 4.5
- 62.6
- Gemini 3.1 Pro
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Coding
Not comparable- Claude Opus 4.5
- 71.7
- Gemini 3.1 Pro
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Reasoning
Not comparable- Claude Opus 4.5
- 64.4
- Gemini 3.1 Pro
- 77.1
- Weighted basis
- 1 vs 1 rows
- Reading
- Not comparable
Knowledge
Not comparable- Claude Opus 4.5
- 58.1
- Gemini 3.1 Pro
- Not measured
- Weighted basis
- 4 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.5
- 85.7
- Gemini 3.1 Pro
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.5
- 69.5
- Gemini 3.1 Pro
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
| Category | Claude Opus 4.5 | Gemini 3.1 Pro | Weighted basis | Reading |
|---|---|---|---|---|
| Multimodal | 69.9 | 82.6 | Like-for-like2 vs 2 rows | Gemini 3.1 Pro leads |
| Math | 57.5 | 31.8 | Directional only4 vs 2 rows | Directional only |
| Agentic | 62.6 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Coding | 71.7 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Reasoning | 64.4 | 77.1 | Not comparable1 vs 1 rows | Not comparable |
| Knowledge | 58.1 | Not measured | Not comparable4 vs 0 rows | Not comparable |
| Multilingual | 85.7 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | 69.5 | Not measured | Not comparable2 vs 0 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
FrontierMath v2 (Tiers 1-3)
Math
MMMU-Pro
Multimodal
Claude Opus 4.5: 70.6%Gemini 3.1 Pro: 83.9%Normalized gap 13.3Claude Opus 4.5 source Gemini 3.1 Pro sourceFrontierMath v2 (Tier 4)
Math
CharXiv
Multimodal
Claude Opus 4.5: 68.5%Gemini 3.1 Pro: 80.2%Normalized gap 11.7Claude Opus 4.5 source Gemini 3.1 Pro source
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude Opus 4.5
- $0.0175
- Fits in one request
- Gemini 3.1 Pro
- $0.008
- Fits in one request
Gemini 3.1 Pro has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 4.5
- $0.325
- Fits in one request
- Gemini 3.1 Pro
- $0.136
- Fits in one request
Gemini 3.1 Pro has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Opus 4.5
- $1.35
- Does not fit in one request
- Cached input priced at the published list-input rate
- Gemini 3.1 Pro
- $0.2
- Fits in one request
Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 4.5Gemini 3.1 Pro
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.5
200K
Gemini 3.1 Pro
API model ID
Claude Opus 4.5
Not sourced
Gemini 3.1 Pro
gemini-3.1-pro-preview
Google Gemini 3.1 Pro Preview model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Opus 4.5
Not published
Gemini 3.1 Pro
$0.2 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Claude Opus 4.5
Not sourced
Gemini 3.1 Pro
text, image, video, audio, pdf
Google Gemini 3.1 Pro Preview model documentationDocumented outputs
Claude Opus 4.5
Not sourced
Gemini 3.1 Pro
Provider availability
Claude Opus 4.5
Not sourced
Gemini 3.1 Pro
Preview · Gemini API, Google AI Studio
Google Gemini model catalogReasoning profile
Claude Opus 4.5
Non-Reasoning
Gemini 3.1 Pro
Reasoning
Weight access
Claude Opus 4.5
Proprietary
Gemini 3.1 Pro
Proprietary
License
Claude Opus 4.5
Proprietary
Gemini 3.1 Pro
Proprietary
Release date
Claude Opus 4.5
2025-11-01
Gemini 3.1 Pro
2026-02-19
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Opus 4.5 has the higher public score estimate, 63.6 versus 56.49, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.136. Cache-heavy agent loop: $1.35 vs $0.2.
- Context tradeoff
- Gemini 3.1 Pro has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence61 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.559.3%SourceGemini 3.1 Pro—Not directly comparable
OSWorld-Verified
Claude Opus 4.566.3%SourceGemini 3.1 Pro—Not directly comparable
OSWorld
Claude Opus 4.566.3%SourceGemini 3.1 Pro—Not directly comparable
Claw-Eval
Claude Opus 4.559.6%SourceGemini 3.1 Pro57.8%SourceClaude Opus 4.5 leads this result
QwenClawBench
Claude Opus 4.552.3%SourceGemini 3.1 Pro—Not directly comparable
τ³-bench results
Claude Opus 4.570.2%SourceGemini 3.1 Pro—Not directly comparable
VITA-Bench
Claude Opus 4.523.3%SourceGemini 3.1 Pro—Not directly comparable
DeepPlanning
Claude Opus 4.526.4%SourceGemini 3.1 Pro—Not directly comparable
Toolathlon
Claude Opus 4.543.5%SourceGemini 3.1 Pro—Not directly comparable
MCP Atlas
Claude Opus 4.542.3%SourceGemini 3.1 Pro—Not directly comparable
MCP-Tasks
Claude Opus 4.571.8%SourceGemini 3.1 Pro—Not directly comparable
WideResearch
Claude Opus 4.576.4%SourceGemini 3.1 Pro—Not directly comparable
CyberGym
Claude Opus 4.550.6%SourceGemini 3.1 Pro—Not directly comparable
Gert Labs
Shared sourceClaude Opus 4.564.23%Gemini 3.1 Pro56.87%Claude Opus 4.5 leads this result
JobBench
Claude Opus 4.532.3%SourceGemini 3.1 Pro—Not directly comparable
DeepSearchQA
Claude Opus 4.5—Gemini 3.1 Pro69.7%SourceNot directly comparable
τ²-bench results
Claude Opus 4.5—Gemini 3.1 Pro95.6%SourceNot directly comparable
ResearchClawBench
Claude Opus 4.5—Gemini 3.1 Pro13.3%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.580.9%SourceGemini 3.1 Pro—Not directly comparable
LiveCodeBench v6
Claude Opus 4.584.8%SourceGemini 3.1 Pro—Not directly comparable
SWE-bench Pro
Claude Opus 4.557.1%SourceGemini 3.1 Pro—Not directly comparable
SWE Multilingual
Claude Opus 4.577.5%SourceGemini 3.1 Pro—Not directly comparable
NL2Repo
Claude Opus 4.543.2%SourceGemini 3.1 Pro—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.5—Gemini 3.1 Pro82.9%SourceNot directly comparable
React Native Evals
Claude Opus 4.5—Gemini 3.1 Pro78.9%SourceNot directly comparable
Vibe Code Bench
Claude Opus 4.5—Gemini 3.1 Pro32.03%SourceNot directly comparable
Reasoning
Knowledge
GPQA
Claude Opus 4.587%SourceGemini 3.1 Pro—Not directly comparable
SuperGPQA
Claude Opus 4.570.6%SourceGemini 3.1 Pro—Not directly comparable
MMLU-Pro
Claude Opus 4.589.5%SourceGemini 3.1 Pro—Not directly comparable
MMLU-Redux
Claude Opus 4.596.6%SourceGemini 3.1 Pro—Not directly comparable
C-Eval
Claude Opus 4.592.2%SourceGemini 3.1 Pro—Not directly comparable
HLE
Claude Opus 4.530.8%SourceGemini 3.1 Pro—Not directly comparable
GPQA-D
Claude Opus 4.5—Gemini 3.1 Pro94.3%SourceNot directly comparable
HLE w/o tools
Claude Opus 4.5—Gemini 3.1 Pro45.4%SourceNot directly comparable
HealthBench Hard
Claude Opus 4.5—Gemini 3.1 Pro20.6%SourceNot directly comparable
MedXpertQA (Text)
Claude Opus 4.5—Gemini 3.1 Pro71.5%SourceNot directly comparable
Math
AIME26
Claude Opus 4.595.1%SourceGemini 3.1 Pro—Not directly comparable
HMMT Feb 2025
Claude Opus 4.592.9%SourceGemini 3.1 Pro—Not directly comparable
HMMT Nov 2025
Claude Opus 4.593.3%SourceGemini 3.1 Pro—Not directly comparable
HMMT Feb 2026
Claude Opus 4.585.3%SourceGemini 3.1 Pro—Not directly comparable
MMAnswerBench
Claude Opus 4.584.0%SourceGemini 3.1 Pro—Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceClaude Opus 4.520.690%Gemini 3.1 Pro36.900%Gemini 3.1 Pro leads this result
FrontierMath v2 (Tier 4)
Shared sourceClaude Opus 4.54.167%Gemini 3.1 Pro16.700%Gemini 3.1 Pro leads this result
Multilingual
Multimodal
MMMU-Pro
Claude Opus 4.570.6%SourceGemini 3.1 Pro83.9%SourceGemini 3.1 Pro leads this result
MathVision
Claude Opus 4.574.3%SourceGemini 3.1 Pro—Not directly comparable
CharXiv
Claude Opus 4.568.5%SourceGemini 3.1 Pro80.2%SourceGemini 3.1 Pro leads this result
VideoMMMU
Claude Opus 4.584.4%SourceGemini 3.1 Pro—Not directly comparable
ScreenSpot Pro
Claude Opus 4.545.7%SourceGemini 3.1 Pro84.4%SourceGemini 3.1 Pro leads this result
V*
Claude Opus 4.567.0%SourceGemini 3.1 Pro—Not directly comparable
ERQA
Claude Opus 4.5—Gemini 3.1 Pro69.4%SourceNot directly comparable
SimpleVQA
Claude Opus 4.5—Gemini 3.1 Pro72.4%SourceNot directly comparable
ZeroBench
Claude Opus 4.5—Gemini 3.1 Pro29.0%SourceNot directly comparable
MedXpertQA (MM)
Claude Opus 4.5—Gemini 3.1 Pro81.3%SourceNot directly comparable
Instruction following
Frequently asked questions
Which is better, Claude Opus 4.5 or Gemini 3.1 Pro?
Claude Opus 4.5 has the higher public score estimate, 63.6 versus 56.49, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Opus 4.5 or Gemini 3.1 Pro?
The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.
Which is better for agentic tasks, Claude Opus 4.5 or Gemini 3.1 Pro?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Claude Opus 4.5 or Gemini 3.1 Pro?
For the stated presets, chat costs $0.0175 on Claude Opus 4.5 and $0.008 on Gemini 3.1 Pro; repository review costs $0.325 and $0.136; the cache-heavy agent loop costs $1.35 and $0.2. Claude Opus 4.5 does not fit this workload in one request. Claude Opus 4.5 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.5 or Gemini 3.1 Pro?
Gemini 3.1 Pro has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated September 3, 2026
Watch Claude Opus 4.5 vs Gemini 3.1 Pro
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.