Model comparison
Claude Fable 5.1 vs Gemini 3.1 Flash Lite
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 36× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
GoogleSummary
- They share 31 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Gemini 3.1 Flash Lite in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 22.9.
- The biggest single-benchmark swing is NYT Connections (extended): 90% for Claude Fable 5.1 and 8.2% for Gemini 3.1 Flash Lite.
- Gemini 3.1 Flash Lite is cheaper at $0.25 / $1.50 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | Gemini 3.1 Flash Lite | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 69.0 | 40.8 |
| Released | 2026-09-01 | 2026-03-03 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $10 | $0.25 |
| Output $ / M tokens | $50 | $1.50 |
| Results tracked | 52 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), Gemini 3.1 Flash Lite: 37.8 (#188)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena WebDev | 1744 | 1256 |
| SciCode | 63.1% | 41.9% |
| WeirdML | 92.9% | 52.2% |
| LMArena Coding | 1528 | 1400 |
| ALE-Bench | 2,143 | 797.73 |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), Gemini 3.1 Flash Lite: 30.2 (#79)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| DeepResearch Bench | — | 37.3% |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), Gemini 3.1 Flash Lite: 22.9 (#186)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| NYT Connections (extended) | 90% | 8.2% |
| CritPt | 31.1% | 1.1% |
| Chess Puzzles | 47% | 25% |
| LMArena Hard Prompts | 1526 | 1407 |
| DTBench | 97.6% | 76.8% |
| LMCA | 65.5% | 35% |
| Epoch Capabilities Index | 164.7 | 144.47 |
| ARC-AGI-2 | 90% | — |
| Kagi LLM Benchmark | — | 67.2% |
| ARC-AGI-1 | 97.5% | — |
| EnigmaEval | — | 3% |
| Thematic Generalization | — | 63.3% |
| EBR-Bench | 57.1% | — |
| Mystery Game Puzzles | 58% | — |
| ForecastBench | — | 54.4 |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), Gemini 3.1 Flash Lite: 40.7 (#90)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 27.7% |
| OTIS Mock AIME 2024-2025 | 100% | 80% |
| LMArena Math | 1525 | 1428 |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Gemini 3.1 Flash Lite: 41.9 (#104)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| Humanity's Last Exam | 46.5% | 8.6% |
| LMArena Expert | 1535 | 1398 |
| GPQA Diamond | — | 81.8% |
| SimpleQA Verified | 70.8% | — |
| Vectara Hallucination Rate | — | 8.2% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), Gemini 3.1 Flash Lite: 39.4 (#60)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Vision | 1318 | 1240 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), Gemini 3.1 Flash Lite: 52.3 (#86)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Non-English | 1507 | 1411 |
| LMArena Chinese | 1586 | 1461 |
| LMArena French | 1525 | 1424 |
| LMArena German | 1500 | 1429 |
| LMArena Japanese | 1543 | 1413 |
| LMArena Korean | 1534 | 1392 |
| LMArena Russian | 1521 | 1420 |
| LMArena Spanish | 1516 | 1421 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), Gemini 3.1 Flash Lite: 72.7 (#131)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1517 | 1377 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), Gemini 3.1 Flash Lite: 42.5 (#122)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1522 | 1394 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), Gemini 3.1 Flash Lite: 60.9 (#94)
| Benchmark | Claude Fable 5.1 | Gemini 3.1 Flash Lite |
|---|---|---|
| LMArena Text | 1510 | 1416 |
| LMArena Creative Writing | 1507 | 1401 |
| LMArena Multi-Turn | 1492 | 1417 |
| EQ-Bench Creative Writing | 2162 | — |
Frequently asked questions
Is Claude Fable 5.1 better than Gemini 3.1 Flash Lite?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 40.8 on the Noometry Index. Gemini 3.1 Flash Lite costs 36× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 or Gemini 3.1 Flash Lite?
Gemini 3.1 Flash Lite is cheaper. It lists at $0.25 per million input tokens and $1.50 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Gemini 3.1 Flash Lite better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Flash Lite does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and Gemini 3.1 Flash Lite share?
31 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Gemini 3.1 Flash Lite has 38.