Model comparison
Claude Opus 4.1 vs Phi-4
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 31.2 on the Noometry Index. Phi-4 costs 343× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
MicrosoftSummary
- They share 24 benchmarks with published results for both. Claude Opus 4.1 scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Opus 4.1 leads 62.4 to 40.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.9% for Claude Opus 4.1 and 13.8% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Opus 4.1 accepts more context: 200K tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Phi-4 | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 41.0 | 31.2 |
| Released | 2025-08-05 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 32K | 4K |
| Input $ / M tokens | $15 | $0.07 |
| Output $ / M tokens | $75 | $0.14 |
| Results tracked | 48 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), Phi-4: 34.4 (#239)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| LMArena Coding | 1479 | 1231 |
| SWE-bench Verified | 73.3% | — |
| LMArena WebDev | 1390 | — |
| WeirdML | 45.9% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), Phi-4: 22.8 (#128)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| Terminal-Bench | 38% | — |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| BALROG | — | 11.6% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), Phi-4: 17.7 (#291)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| Chess Puzzles | 7% | 1% |
| LMArena Hard Prompts | 1443 | 1220 |
| Epoch Capabilities Index | 144.12 | 130.42 |
| SimpleBench | 60% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| LiveBench Reasoning | — | 47.8% |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 37.1% | — |
| ForecastBench | 62 | — |
| LiveBench | — | 41.6% |
Math Claude Opus 4.1 leads
Claude Opus 4.1: 22.3 (#277), Phi-4: 20.8 (#285)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 13.8% |
| LMArena Math | 1431 | 1246 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 42.0 (#101), Phi-4: 32.6 (#209)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| GPQA Diamond | 77.3% | 56.1% |
| Confabulations | 17.1% | 29.4% |
| Vectara Hallucination Rate | 11.8% | 3.7% |
| LMArena Expert | 1439 | 1203 |
| Humanity's Last Exam | 11.5% | — |
| MMLU | — | 84.8% |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), Phi-4: —
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| VPCT | 35% | — |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.0 (#95), Phi-4: 37.2 (#237)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1405 | 1197 |
| LMArena Chinese | 1427 | 1212 |
| LMArena French | 1431 | 1224 |
| LMArena German | 1413 | 1222 |
| LMArena Japanese | 1378 | 1158 |
| LMArena Korean | 1380 | 1151 |
| LMArena Russian | 1422 | 1209 |
| LMArena Spanish | 1448 | 1234 |
Instruction Following Claude Opus 4.1 leads
Claude Opus 4.1: 75.6 (#58), Phi-4: 60.4 (#251)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), Phi-4: 36.9 (#226)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1455 | 1217 |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), Phi-4: 40.5 (#244)
| Benchmark | Claude Opus 4.1 | Phi-4 |
|---|---|---|
| LMArena Text | 1419 | 1217 |
| LMArena Creative Writing | 1412 | 1182 |
| Short-Story Creative Writing | 84.7% | 62.6% |
| LMArena Multi-Turn | 1444 | 1206 |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Claude Opus 4.1 better than Phi-4?
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 31.2 on the Noometry Index. Phi-4 costs 343× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.1 or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Phi-4 better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4.1 does, with 200K tokens against 128K.
How many benchmarks do Claude Opus 4.1 and Phi-4 share?
24 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Phi-4 has 37.