Model comparison
Claude Fable 5 vs Gemini 3.7 Flash
Claude Fable 5 is the stronger model overall, scoring 66.8 to 59.8 on the Noometry Index. Gemini 3.7 Flash costs 13× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
GoogleSummary
- They share 44 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and Gemini 3.7 Flash in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Fable 5 leads 88.5 to 69.6.
- The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 36.6% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5 | Gemini 3.7 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 66.8 | 59.8 |
| Released | 2026-06-07 | 2026-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $10 | $0.75 |
| Output $ / M tokens | $50 | $3.75 |
| Results tracked | 62 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), Gemini 3.7 Flash: 56.2 (#22)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| DeepSWE | 69.9% | 65.5% |
| FrontierCode | 53.5% | 43.6% |
| LMArena WebDev | 1625 | 1592 |
| FrontierSWE | 47% | 20.3% |
| SciCode | 61% | 59.8% |
| LMArena Coding | 1519 | 1497 |
| ALE-Bench | 2,041 | 904.3 |
| GSO | 78.4% | — |
| WeirdML | 91.9% | — |
| MirrorCode | 63.9% | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.0 (#2), Gemini 3.7 Flash: 42.1 (#19)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | 63.6% | 67.8% |
| Remote Labor Index | 16.1% | 5% |
| GDP.pdf | 30% | 23.8% |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), Gemini 3.7 Flash: 70.0 (#15)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 89.2% | 84.6% |
| NYT Connections (extended) | 92.7% | 94% |
| ARC-AGI-1 | 98.5% | 95.5% |
| CritPt | 28.6% | 14.3% |
| Chess Puzzles | 41% | 47% |
| LMArena Hard Prompts | 1508 | 1494 |
| Mystery Game Puzzles | 52% | 37% |
| DTBench | 98.4% | 96.8% |
| LMCA | 61.1% | 50.4% |
| Epoch Capabilities Index | 162.06 | 157.27 |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| EnigmaEval | 39.3% | — |
| EBR-Bench | 39.5% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), Gemini 3.7 Flash: 69.6 (#23)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 71.6% |
| FrontierMath Tier 4 | 90.2% | 36.6% |
| OTIS Mock AIME 2024-2025 | 100% | 97.2% |
| ProofBench | 95% | 58% |
| LMArena Math | 1519 | 1507 |
| FrontierMath Erdős | 0% | — |
Knowledge Gemini 3.7 Flash leads
Claude Fable 5: 62.2 (#25), Gemini 3.7 Flash: 69.7 (#5)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 85.9% | 94.8% |
| SimpleQA Verified | 70.7% | 69.2% |
| LMArena Expert | 1534 | 1508 |
Multimodal Claude Fable 5 leads
Claude Fable 5: 45.3 (#17), Gemini 3.7 Flash: 37.3 (#73)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1324 | 1316 |
| Furniture Assembly | 35.8% | 26.7% |
| Blueprint-Bench 2 | 38.6% | — |
| LMArena Document | 1496 | — |
Multilingual Too close to call
Claude Fable 5: 57.3 (#9), Gemini 3.7 Flash: 57.6 (#7)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1481 | 1484 |
| LMArena Chinese | 1543 | 1548 |
| LMArena French | 1505 | 1505 |
| LMArena German | 1486 | 1498 |
| LMArena Japanese | 1506 | 1512 |
| LMArena Korean | 1488 | 1483 |
| LMArena Russian | 1504 | 1516 |
| LMArena Spanish | 1498 | 1503 |
Instruction Following Too close to call
Claude Fable 5: 78.6 (#8), Gemini 3.7 Flash: 77.7 (#15)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1502 | 1483 |
Long Context Too close to call
Claude Fable 5: 46.3 (#23), Gemini 3.7 Flash: 45.7 (#30)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1509 | 1492 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), Gemini 3.7 Flash: 71.2 (#20)
| Benchmark | Claude Fable 5 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1491 | 1486 |
| LMArena Creative Writing | 1494 | 1490 |
| EQ-Bench Creative Writing | 1943 | 1723 |
| LMArena Multi-Turn | 1504 | 1489 |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than Gemini 3.7 Flash?
Claude Fable 5 is the stronger model overall, scoring 66.8 to 59.8 on the Noometry Index. Gemini 3.7 Flash costs 13× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 or Gemini 3.7 Flash?
Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Fable 5 lists at $10 and $50.
Is Claude Fable 5 or Gemini 3.7 Flash better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 56.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.7 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5 and Gemini 3.7 Flash share?
44 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Gemini 3.7 Flash has 44.