Model comparison
Claude Fable 5.1 vs GPT-4.1 mini
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 29× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-4.1 mini 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 10.8.
- The biggest single-benchmark swing is ARC-AGI-1: 97.5% for Claude Fable 5.1 and 3.5% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | GPT-4.1 mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 33.6 |
| Released | 2026-09-01 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 33K |
| Input $ / M tokens | $10 | $0.40 |
| Output $ / M tokens | $50 | $1.60 |
| Results tracked | 52 | 47 |
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), GPT-4.1 mini: 30.6 (#293)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| SciCode | 63.1% | 40.4% |
| WeirdML | 92.9% | 37.6% |
| LMArena Coding | 1528 | 1367 |
| FrontierCode | 50.9% | — |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| BigCodeBench Instruct | — | 48.9% |
| MirrorCode | 73.3% | — |
| CadEval | — | 16% |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), GPT-4.1 mini: 33.3 (#55)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| APEX-Agents | 68.6% | — |
| Berkeley Function Calling Leaderboard | — | 50.5% |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| Vending-Bench 2 | 5,422 | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), GPT-4.1 mini: 10.8 (#340)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 90% | 0% |
| ARC-AGI-1 | 97.5% | 3.5% |
| CritPt | 31.1% | 0% |
| Chess Puzzles | 47% | 7% |
| LMArena Hard Prompts | 1526 | 1349 |
| Mystery Game Puzzles | 58% | 7% |
| DTBench | 97.6% | 68.8% |
| LMCA | 65.5% | 21.1% |
| Epoch Capabilities Index | 164.7 | 135.01 |
| Kagi LLM Benchmark | — | 48.6% |
| NYT Connections (extended) | 90% | — |
| EBR-Bench | 57.1% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), GPT-4.1 mini: 24.1 (#270)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 6.7% |
| OTIS Mock AIME 2024-2025 | 100% | 44.7% |
| LMArena Math | 1525 | 1343 |
| FrontierMath Tier 4 | 87.8% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), GPT-4.1 mini: 34.7 (#194)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| SimpleQA Verified | 70.8% | 12.7% |
| LMArena Expert | 1535 | 1338 |
| GPQA Diamond | — | 65.8% |
| Humanity's Last Exam | 46.5% | — |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), GPT-4.1 mini: 35.8 (#82)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | 1318 | 1181 |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), GPT-4.1 mini: 45.7 (#166)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1507 | 1318 |
| LMArena Chinese | 1586 | 1329 |
| LMArena French | 1525 | 1358 |
| LMArena German | 1500 | 1351 |
| LMArena Japanese | 1543 | 1290 |
| LMArena Korean | 1534 | 1298 |
| LMArena Russian | 1521 | 1324 |
| LMArena Spanish | 1516 | 1319 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), GPT-4.1 mini: 73.7 (#118)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1517 | 1333 |
| IFEval | — | 90.4% |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), GPT-4.1 mini: 31.8 (#275)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1522 | 1344 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), GPT-4.1 mini: 48.6 (#199)
| Benchmark | Claude Fable 5.1 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1510 | 1340 |
| LMArena Creative Writing | 1507 | 1300 |
| EQ-Bench Creative Writing | 2162 | 1147 |
| LMArena Multi-Turn | 1492 | 1354 |
| WildBench | — | 83.8% |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-4.1 mini?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 29× 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 GPT-4.1 mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-4.1 mini better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and GPT-4.1 mini share?
32 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-4.1 mini has 47.