Model comparison
Claude Fable 5 vs Gemini 3.1 Pro
Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use BenchLM's provisional ranking lane.
Verified leaderboard positions: Claude Fable 5 #2; Gemini 3.1 Pro unranked
Evidence parity. Claude Fable 5 and Gemini 3.1 Pro share 4 comparable benchmark results. 2 of 8 categories are comparable. 16 results are unique to Claude Fable 5; 44 to Gemini 3.1 Pro.
Updated July 13, 2026- Shared results
- 4
- Claude Fable 5 only
- 16
- Gemini 3.1 Pro only
- 44
- Comparable categories
- 2 / 8
Pick Claude Fable 5 if you want the stronger benchmark profile. Gemini 3.1 Pro only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Claude Fable 5 has the cleaner provisional overall profile here, landing at 91 versus 88. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Claude Fable 5's sharpest advantage is in mathematics, where it averages 97.6 against 31.8. The single biggest benchmark swing on the page is CharXiv, 93.2% to 80.2%.
Claude Fable 5 is also the more expensive model on tokens at $10.00 input / $50.00 output per 1M tokens, versus $2.00 input / $12.00 output per 1M tokens for Gemini 3.1 Pro. That is roughly 4.2x on output cost alone. Claude Fable 5 is the reasoning model in the pair, while Gemini 3.1 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Claude Fable 5 gives you the larger context window at 1M+, compared with 1M for Gemini 3.1 Pro.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Claude Fable 5 | Δ | Gemini 3.1 Pro |
|---|---|---|---|
| Math | Claude Fable 597.6 | Margin← 65.8 | Gemini 3.1 Pro31.8 |
| Multimodal | Claude Fable 592.9 | Margin← 10.3 | Gemini 3.1 Pro82.6 |
| Agentic | Claude Fable 585.3 | MarginNo overlap | Gemini 3.1 ProNot measured |
| Coding | Claude Fable 585.6 | MarginNo overlap | Gemini 3.1 ProNot measured |
| Reasoning | Claude Fable 5Not measured | MarginNo overlap | Gemini 3.1 Pro77.1 |
| Knowledge | Claude Fable 568.6 | MarginNo overlap | Gemini 3.1 ProNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
CharXiv
MultimodalA 93.2%B 80.2%Winner: Claude Fable 5Δ 13CharXiv: Claude Fable 5 scored 93.2%; Gemini 3.1 Pro scored 80.2%. Claude Fable 5 wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 92.7%B 83.9%Winner: Claude Fable 5Δ 8.8MMMU-Pro: Claude Fable 5 scored 92.7%; Gemini 3.1 Pro scored 83.9%. Claude Fable 5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Claude Fable 5 | Gemini 3.1 Pro | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Claude Fable 5$10 input / $50 output | Gemini 3.1 Pro$2 input / $12 output | Gemini 3.1 Pro has the lower combined listed price. |
| Generation speedtokens per second | Claude Fable 5Not available | Gemini 3.1 Pro109 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Claude Fable 5Not available | Gemini 3.1 Pro29.71 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Claude Fable 51M+ | Gemini 3.1 Pro1M | Listed context windows are equal. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.1 Pro | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 84.3% | — | Not comparable |
| OSWorld-VerifiedSource | 85% | — | Not comparable |
| BrowseCompSource | 86.9% | — | Not comparable |
| GDPval-AASource | 1760 | 962 | Claude Fable 5 leads |
| Claw-EvalSource | — | 57.8% | Not comparable |
| DeepSearchQASource | — | 69.7% | Not comparable |
| Tau2-TelecomSource | — | 95.6% | Not comparable |
| AA Agentic IndexSource | — | 21.4% | Not comparable |
| APEX-Agents-AASource | — | 32.0% | Not comparable |
| GDPval-AASource | — | 23.1% | Not comparable |
| Gert LabsSource | — | 56.87% | Not comparable |
| ResearchClawBenchSource | — | 13.3% | Not comparable |
| AA AutomationBenchSource | — | 37.5% | Not comparable |
| AA EnterpriseOps-GymSource | — | 42.2% | Not comparable |
| AA Harvey LABSource | — | 0.0% | Not comparable |
| AA ITBenchSource | — | 30.3% | Not comparable |
| AA Tau3 BankingSource | — | 16.5% | Not comparable |
Coding13 benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.1 Pro | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 95% | — | Not comparable |
| SWE-bench ProSource | 80% | — | Not comparable |
| FrontierCodeSource | 53.5% | — | Not comparable |
| Terminal-Bench 2.0Source | 84.3% | — | Not comparable |
| cursorBench31Source | 70.6% | — | Not comparable |
| cursorBench32Source | 70.5% | — | Not comparable |
| LiveCodeBench ProSource | — | 82.9% | Not comparable |
| React Native EvalsSource | — | 78.9% | Not comparable |
| Vibe Code BenchSource | — | 32.03% | Not comparable |
| AA Coding IndexSource | — | 68.8% | Not comparable |
| Terminal-Bench HardSource | — | 53.8% | Not comparable |
| AA-SciCodeSource | — | 58.9% | Not comparable |
| AA Terminal-Bench 2.1Source | — | 73.8% | Not comparable |
Reasoning3 benchmarks
Knowledge12 benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.1 Pro | Result |
|---|---|---|---|
| GPQASource | 94.5% | — | Not comparable |
| HLESource | 64.5% | — | Not comparable |
| HLE w/o toolsSource | 59% | 45.4% | Claude Fable 5 leads |
| GPQA-DSource | — | 94.3% | Not comparable |
| HealthBench HardSource | — | 20.6% | Not comparable |
| MedXpertQA (Text)Source | — | 71.5% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 46.5% | Not comparable |
| AA-GPQA DiamondSource | — | 94.1% | Not comparable |
| AA-HLESource | — | 44.7% | Not comparable |
| AA-Omniscience IndexSource | — | 32.9% | Not comparable |
| AA-Omniscience AccuracySource | — | 55.3% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 49.9% | Not comparable |
MathClaude Fable 5 wins3 benchmarks
Multilingual2 benchmarks
MultimodalClaude Fable 5 wins13 benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.1 Pro | Result |
|---|---|---|---|
| MMMU-ProSource | 92.7% | 83.9% | Claude Fable 5 leads |
| SWE-bench MultimodalSource | 59% | — | Not comparable |
| CharXivSource | 93.2% | 80.2% | Claude Fable 5 leads |
| CharXiv w/o toolsSource | 86.1% | — | Not comparable |
| Blueprint-Bench 2Source | 38.6% | — | Not comparable |
| ERQASource | — | 69.4% | Not comparable |
| SimpleVQASource | — | 72.4% | Not comparable |
| ScreenSpot ProSource | — | 84.4% | Not comparable |
| ZeroBenchSource | — | 29.0% | Not comparable |
| MedXpertQA (MM)Source | — | 81.3% | Not comparable |
| GDPval-AASource | — | 1320 | Not comparable |
| AA-MMMU-ProSource | — | 82.4% | Not comparable |
| Design Arena WebsiteSource | — | 1294 | Not comparable |
Inst. Following1 benchmarks
| Benchmark | Claude Fable 5 | Gemini 3.1 Pro | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 77.1% | Not comparable |
Frequently Asked Questions (3)
Which is better, Claude Fable 5 or Gemini 3.1 Pro?
Claude Fable 5 is ahead on BenchLM's provisional leaderboard, 91 to 88. The biggest single separator in this matchup is CharXiv, where the scores are 93.2% and 80.2%.
Which is better for math, Claude Fable 5 or Gemini 3.1 Pro?
Claude Fable 5 has the edge for math in this comparison, averaging 97.6 versus 31.8. Gemini 3.1 Pro stays close enough that the answer can still flip depending on your workload.
Which is better for multimodal and grounded tasks, Claude Fable 5 or Gemini 3.1 Pro?
Claude Fable 5 has the edge for multimodal and grounded tasks in this comparison, averaging 92.9 versus 82.6. Inside this category, CharXiv is the benchmark that creates the most daylight between them.
Related Comparisons
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.