Model comparison
Claude Fable 5.1 vs Phi-4 Mini
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 30.9 on the Noometry Index. Phi-4 Mini costs 152× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
MicrosoftSummary
- They share 2 benchmarks with published results for both. Claude Fable 5.1 scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 22.4.
- The biggest single-benchmark swing is SciCode: 63.1% for Claude Fable 5.1 and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | Phi-4 Mini | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 69.0 | 30.9 |
| Released | 2026-09-01 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 1M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $10 | $0.075 |
| Output $ / M tokens | $50 | $0.30 |
| Results tracked | 52 | 3 |
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), Phi-4 Mini: 28.1 (#317)
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| SciCode | 63.1% | 10.8% |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| LMArena WebDev | 1744 | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| LMArena Coding | 1528 | — |
| MirrorCode | 73.3% | — |
| ALE-Bench | 2,143 | — |
Agentic & Tool Use Not comparable
Claude Fable 5.1: 50.7 (#5), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| APEX-Agents | 68.6% | — |
| 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), Phi-4 Mini: 22.4 (#195)
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| CritPt | 31.1% | 0% |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| LMArena Hard Prompts | 1526 | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
| Epoch Capabilities Index | 164.7 | — |
Math Not comparable
Claude Fable 5.1: 89.6 (#4), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LMArena Math | 1525 | — |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), Phi-4 Mini: 25.3 (#262)
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1535 | — |
Multimodal Not comparable
Claude Fable 5.1: 53.9 (#4), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Not comparable
Claude Fable 5.1: 59.1 (#3), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1507 | — |
| LMArena Chinese | 1586 | — |
| LMArena French | 1525 | — |
| LMArena German | 1500 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
| LMArena Russian | 1521 | — |
| LMArena Spanish | 1516 | — |
Instruction Following Not comparable
Claude Fable 5.1: 79.2 (#6), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1517 | — |
Long Context Not comparable
Claude Fable 5.1: 46.7 (#20), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1522 | — |
Writing & Preference Not comparable
Claude Fable 5.1: 79.2 (#2), Phi-4 Mini: —
| Benchmark | Claude Fable 5.1 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1510 | — |
| LMArena Creative Writing | 1507 | — |
| EQ-Bench Creative Writing | 2162 | — |
| LMArena Multi-Turn | 1492 | — |
Frequently asked questions
Is Claude Fable 5.1 better than Phi-4 Mini?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 30.9 on the Noometry Index. Phi-4 Mini costs 152× 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 Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or Phi-4 Mini better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5.1 does, with 1M tokens against 128K.
How many benchmarks do Claude Fable 5.1 and Phi-4 Mini share?
2 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Phi-4 Mini has 3.