Model comparison
Claude Haiku 4.5 vs Phi-4 Mini
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 15× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 2 categories and Phi-4 Mini in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Haiku 4.5 leads 44.0 to 28.1.
- The biggest single-benchmark swing is SciCode: 43.3% for Claude Haiku 4.5 and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Phi-4 Mini | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 39.5 | 30.9 |
| Released | 2025-10-15 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 64K | 4K |
| Input $ / M tokens | $1 | $0.075 |
| Output $ / M tokens | $5 | $0.30 |
| Results tracked | 53 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Phi-4 Mini: 28.1 (#317)
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| SciCode | 43.3% | 10.8% |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
| LMArena Coding | 1453 | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Phi-4 Mini leads
Claude Haiku 4.5: 15.1 (#320), Phi-4 Mini: 22.4 (#195)
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| CritPt | 0% | 0% |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| LMArena Hard Prompts | 1420 | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Not comparable
Claude Haiku 4.5: 44.9 (#78), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Phi-4 Mini: 25.3 (#262)
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 9.8% | 23.5% |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1377 | — |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1381 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Not comparable
Claude Haiku 4.5: 71.4 (#149), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| IFEval | 80.1% | — |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
Claude Haiku 4.5: 43.6 (#92), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1427 | — |
Writing & Preference Not comparable
Claude Haiku 4.5: 57.9 (#123), Phi-4 Mini: —
| Benchmark | Claude Haiku 4.5 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Phi-4 Mini?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 15× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 4.5 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 Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Phi-4 Mini better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 128K.
How many benchmarks do Claude Haiku 4.5 and Phi-4 Mini share?
3 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Phi-4 Mini has 3.