Key implications
Insufficient shared-metric coverage. Each finding is tied to a published metric, price, context, or modality fact.
- Input API price: Gemini 3.5 Flash has the lower verified rate ($1.5 / 1M tokens vs $5 / 1M tokens).
- Output API price: Gemini 3.5 Flash has the lower verified rate ($9 / 1M tokens vs $25 / 1M tokens).
Shared metric view
A radar is shown only when at least four compatible supported score metrics are published.
Comparable metric detail
- AgenticClaude Opus 4.7: 58.5 · Gemini 3.5 Flash: 44.9
- CodingClaude Opus 4.7: 68.72 · Gemini 3.5 Flash: 62.33
- InstructionFollowingClaude Opus 4.7: Unavailable · Gemini 3.5 Flash: 82.4
- KnowledgeClaude Opus 4.7: 63.9 · Gemini 3.5 Flash: 60.4
- MathClaude Opus 4.7: 61.8 · Gemini 3.5 Flash: 55.9
- MultimodalGroundedClaude Opus 4.7: Unavailable · Gemini 3.5 Flash: 80.6
- ReasoningClaude Opus 4.7: Unavailable · Gemini 3.5 Flash: 62.6
- OverallClaude Opus 4.7: 72.33 · Gemini 3.5 Flash: 64.73
Source metrics
Friendly metric names and published units stay visible. Missing measurements remain unavailable rather than becoming a score.
Source metric comparison| Metric | Unit | Claude Opus 4.7 | Gemini 3.5 Flash |
|---|
| Agentic | score | 58.5 | 44.9 |
|---|
| Coding | score | 68.72 | 62.33 |
|---|
| InstructionFollowing | score | Unavailable | 82.4 |
|---|
| Knowledge | score | 63.9 | 60.4 |
|---|
| Math | score | 61.8 | 55.9 |
|---|
| MultimodalGrounded | score | Unavailable | 80.6 |
|---|
| Reasoning | score | Unavailable | 62.6 |
|---|
| Overall | score | 72.33 | 64.73 |
|---|
Agentic
- Unit
- score
- Claude Opus 4.7
- 58.5
- Gemini 3.5 Flash
- 44.9
Coding
- Unit
- score
- Claude Opus 4.7
- 68.72
- Gemini 3.5 Flash
- 62.33
InstructionFollowing
- Unit
- score
- Claude Opus 4.7
- Unavailable
- Gemini 3.5 Flash
- 82.4
Knowledge
- Unit
- score
- Claude Opus 4.7
- 63.9
- Gemini 3.5 Flash
- 60.4
Math
- Unit
- score
- Claude Opus 4.7
- 61.8
- Gemini 3.5 Flash
- 55.9
MultimodalGrounded
- Unit
- score
- Claude Opus 4.7
- Unavailable
- Gemini 3.5 Flash
- 80.6
Reasoning
- Unit
- score
- Claude Opus 4.7
- Unavailable
- Gemini 3.5 Flash
- 62.6
Overall
- Unit
- score
- Claude Opus 4.7
- 72.33
- Gemini 3.5 Flash
- 64.73
Pricing and context
Verification is shown beside each selected route. Missing facts remain Not verified.
Route pricing and context comparison| Field | Unit | Claude Opus 4.7 | Gemini 3.5 Flash |
|---|
| Input API price | USD / 1M tokens | $5 | $1.5 |
|---|
| Cached input API price | USD / 1M tokens | Not verified | $0.15 |
|---|
| Output API price | USD / 1M tokens | $25 | $9 |
|---|
| Route context | tokens | 1,000,000 | 1,000,000 |
|---|
| 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 4.7
- $5
- Gemini 3.5 Flash
- $1.5
Cached input API price
- Unit
- USD / 1M tokens
- Claude Opus 4.7
- Not verified
- Gemini 3.5 Flash
- $0.15
Output API price
- Unit
- USD / 1M tokens
- Claude Opus 4.7
- $25
- Gemini 3.5 Flash
- $9
Route context
- Unit
- tokens
- Claude Opus 4.7
- 1,000,000
- Gemini 3.5 Flash
- 1,000,000
Input modalities
- Unit
- published list
- Claude Opus 4.7
- Not verified
- Gemini 3.5 Flash
- Not verified
Output modalities
- Unit
- published list
- Claude Opus 4.7
- Not verified
- Gemini 3.5 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 4.7 — source benchlm · artifact models · model claude-opus-4-7
- Gemini 3.5 Flash — source benchlm · artifact models · model gemini-3-5-flash
- Selected price routes
- Claude Opus 4.7 — route benchlm:claude-opus-4-7 · source benchlm · provider anthropic
- Gemini 3.5 Flash — route benchlm:gemini-3-5-flash · source benchlm · provider google
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.