A
Anthropic
Claude Fable 5
- Model type
- Proprietary
- Evidence state
- Supported evidence
- Published context
- 1,000,000
Claude Fable 5 vs
Gemini 3.1 Pro
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 3.1 Pro
- Model type
- Proprietary
- Evidence state
- Estimated evidence
- Published context
- 1,000,000
Key implications
Insufficient shared-metric coverage. Each finding is tied to a published metric, price, context, or modality fact.
- Input API price: Gemini 3.1 Pro has the lower verified rate ($2 / 1M tokens vs $10 / 1M tokens).
- Output API price: Gemini 3.1 Pro has the lower verified rate ($12 / 1M tokens vs $50 / 1M tokens).
Shared metric view
A radar is shown only when at least four compatible supported score metrics are published.
Comparable metric detail
- AgenticClaude Fable 5: 75.54 · Gemini 3.1 Pro: 33.84
- CodingClaude Fable 5: 81.41 · Gemini 3.1 Pro: 49.3
- KnowledgeClaude Fable 5: 67.4 · Gemini 3.1 Pro: 66.7
- MathClaude Fable 5: Unavailable · Gemini 3.1 Pro: 55.1
- MultimodalGroundedClaude Fable 5: 60.8 · Gemini 3.1 Pro: 76.8
- ReasoningClaude Fable 5: Unavailable · Gemini 3.1 Pro: 72.4
- OverallClaude Fable 5: 83.15 · Gemini 3.1 Pro: 56.25
Source metrics
Friendly metric names and published units stay visible. Missing measurements remain unavailable rather than becoming a score.
| Metric | Unit | Claude Fable 5 | Gemini 3.1 Pro |
|---|---|---|---|
| Agentic | score | 75.54 | 33.84 |
| Coding | score | 81.41 | 49.3 |
| Knowledge | score | 67.4 | 66.7 |
| Math | score | Unavailable | 55.1 |
| MultimodalGrounded | score | 60.8 | 76.8 |
| Reasoning | score | Unavailable | 72.4 |
| Overall | score | 83.15 | 56.25 |
Agentic
- Unit
- score
- Claude Fable 5
- 75.54
- Gemini 3.1 Pro
- 33.84
Coding
- Unit
- score
- Claude Fable 5
- 81.41
- Gemini 3.1 Pro
- 49.3
Knowledge
- Unit
- score
- Claude Fable 5
- 67.4
- Gemini 3.1 Pro
- 66.7
Math
- Unit
- score
- Claude Fable 5
- Unavailable
- Gemini 3.1 Pro
- 55.1
MultimodalGrounded
- Unit
- score
- Claude Fable 5
- 60.8
- Gemini 3.1 Pro
- 76.8
Reasoning
- Unit
- score
- Claude Fable 5
- Unavailable
- Gemini 3.1 Pro
- 72.4
Overall
- Unit
- score
- Claude Fable 5
- 83.15
- Gemini 3.1 Pro
- 56.25
Pricing and context
Verification is shown beside each selected route. Missing facts remain Not verified.
| Field | Unit | Claude Fable 5 | Gemini 3.1 Pro |
|---|---|---|---|
| Input API price | USD / 1M tokens | $10 | $2 |
| Cached input API price | USD / 1M tokens | $1 | $0.2 |
| Output API price | USD / 1M tokens | $50 | $12 |
| 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 Fable 5
- $10
- Gemini 3.1 Pro
- $2
Cached input API price
- Unit
- USD / 1M tokens
- Claude Fable 5
- $1
- Gemini 3.1 Pro
- $0.2
Output API price
- Unit
- USD / 1M tokens
- Claude Fable 5
- $50
- Gemini 3.1 Pro
- $12
Route context
- Unit
- tokens
- Claude Fable 5
- 1,000,000
- Gemini 3.1 Pro
- 1,000,000
Input modalities
- Unit
- published list
- Claude Fable 5
- Not verified
- Gemini 3.1 Pro
- Not verified
Output modalities
- Unit
- published list
- Claude Fable 5
- Not verified
- Gemini 3.1 Pro
- 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 Fable 5 — source benchlm · artifact models · model claude-fable-5
- Gemini 3.1 Pro — source benchlm · artifact models · model gemini-3-1-pro
- Selected price routes
- Claude Fable 5 — route benchlm:claude-fable-5 · source benchlm · provider anthropic
- Gemini 3.1 Pro — route benchlm:gemini-3-1-pro · source benchlm · provider google
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.