A
Anthropic
Claude Opus 5
- Model type
- Proprietary
- Evidence state
- Supported evidence
- Published context
- Not verified
Claude Opus 5 vs
Gemini 3.7 Flash
Read the published evidence, route context, and missing facts before making a local decision. This page does not name a universal winner.
Models in this comparison
Provider identity and evidence state stay balanced across the pair.
GGoogle
Gemini 3.7 Flash
- Model type
- Unknown
- Evidence state
- Estimated evidence
- Published context
- Not verified
Key implications
Insufficient shared-metric coverage. Each finding is tied to a published metric, price, context, or modality fact.
No decision-relevant implication can be verified for this pair yet.
Shared metric view
A radar is shown only when at least four compatible supported score metrics are published.
Comparable metric detail
- AgenticClaude Opus 5: 80.13 · Gemini 3.7 Flash: 56.01
- CodingClaude Opus 5: 78.41 · Gemini 3.7 Flash: 66.82
- KnowledgeClaude Opus 5: 97 · Gemini 3.7 Flash: 66.8
- MultimodalGroundedClaude Opus 5: 85.9 · Gemini 3.7 Flash: 69.9
- ReasoningClaude Opus 5: 83.5 · Gemini 3.7 Flash: Unavailable
- OverallClaude Opus 5: 83.06 · Gemini 3.7 Flash: 61.4
Source metrics
Friendly metric names and published units stay visible. Missing measurements remain unavailable rather than becoming a score.
| Metric | Unit | Claude Opus 5 | Gemini 3.7 Flash |
|---|---|---|---|
| Agentic | score | 80.13 | 56.01 |
| Coding | score | 78.41 | 66.82 |
| Knowledge | score | 97 | 66.8 |
| MultimodalGrounded | score | 85.9 | 69.9 |
| Reasoning | score | 83.5 | Unavailable |
| Overall | score | 83.06 | 61.4 |
Agentic
- Unit
- score
- Claude Opus 5
- 80.13
- Gemini 3.7 Flash
- 56.01
Coding
- Unit
- score
- Claude Opus 5
- 78.41
- Gemini 3.7 Flash
- 66.82
Knowledge
- Unit
- score
- Claude Opus 5
- 97
- Gemini 3.7 Flash
- 66.8
MultimodalGrounded
- Unit
- score
- Claude Opus 5
- 85.9
- Gemini 3.7 Flash
- 69.9
Reasoning
- Unit
- score
- Claude Opus 5
- 83.5
- Gemini 3.7 Flash
- Unavailable
Overall
- Unit
- score
- Claude Opus 5
- 83.06
- Gemini 3.7 Flash
- 61.4
Pricing and context
Verification is shown beside each selected route. Missing facts remain Not verified.
| Field | Unit | Claude Opus 5 | Gemini 3.7 Flash |
|---|---|---|---|
| Input API price | USD / 1M tokens | $5 | Not verified |
| Cached input API price | USD / 1M tokens | $0.5 | Not verified |
| Output API price | USD / 1M tokens | $25 | Not verified |
| Route context | tokens | 1,000,000 | Not verified |
| Input modalities | published list | Not verified | Not verified |
| Output modalities | published list | Not verified | Not verified |
Input API price
- Unit
- USD / 1M tokens
- Claude Opus 5
- $5
- Gemini 3.7 Flash
- Not verified
Cached input API price
- Unit
- USD / 1M tokens
- Claude Opus 5
- $0.5
- Gemini 3.7 Flash
- Not verified
Output API price
- Unit
- USD / 1M tokens
- Claude Opus 5
- $25
- Gemini 3.7 Flash
- Not verified
Route context
- Unit
- tokens
- Claude Opus 5
- 1,000,000
- Gemini 3.7 Flash
- Not verified
Input modalities
- Unit
- published list
- Claude Opus 5
- Not verified
- Gemini 3.7 Flash
- Not verified
Output modalities
- Unit
- published list
- Claude Opus 5
- Not verified
- Gemini 3.7 Flash
- Not verified
Evidence provenance
Source records, route identity, timestamps, and methodology are consolidated here without declaring either model a winner.
- Publication time
- Aug 30, 2026, 2:15 AM UTC
- Freshness
- Stale — Published weekly benchmark evidence has not refreshed within 8 days.
- Methodology
- benchlm: benchlm_raw_composite
- Model records
- Claude Opus 5 — source benchlm · artifact models · model claude-opus-5
- Gemini 3.7 Flash — source benchlm · artifact models · model gemini-3-7-flash
- Selected price routes
- Claude Opus 5 — route benchlm:claude-opus-5 · source benchlm · provider anthropic
- Gemini 3.7 Flash — Not published
Keep comparing
Other reviewed matchups from the same published revision, ready to open without changing this result’s evidence.
Switch model pair
Choose from this result’s current and reviewed related models. Switching opens a reviewed comparison; it does not change this result’s evidence.
Step 1
Start with popular models, or search the full selectable directory.
Step 2
Start with popular models, or search the full selectable directory.