Phi-4 on HumanEval: score, rank and what it means
Phi-4 scores 79.4 on HumanEval, placing it #253 of 600 models in the index. The benchmark average is 74.0 and the leader is GPT-5.2 Pro at 96.8.
Score distribution
The chart shows the top 10 models on HumanEval, with Phi-4 highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 2 | Gemini 3 Pro Pro | Google DeepMind | 200000 | $19.80 | 87.3 |
| 3 | o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
| 4 | Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| 5 | Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| 6 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 7 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 8 | Grok 4 Max | xAI | 2000000 | $19.70 | 86.6 |
| 9 | GPT-5.2 Turbo | OpenAI | 1000000 | $20.73 | 87.4 |
| 10 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
What this score means
On HumanEval, Phi-4 sits at #253 of 600. The leader, GPT-5.2 Pro, scores 96.8, so the gap to the top is 17.4 points. The median model in this index scores 77.4, which puts Phi-4 above the midpoint.
Microsoft models average 66.6 on this benchmark. Phi-4 is 12.8 points above that provider line, so it is a stronger result than the average Microsoft model.
Among multimodal models, the average is 82.2. Phi-4 is 2.8 points below that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 79.4 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.
Price context
At $3.96 per million input tokens, Phi-4 is below the median input price of $4.00 across the 600 models scored on HumanEval. The models immediately around it in the ranking are shown below so you can compare score and price together.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Yi-Large Chat | 01.AI | 65536 | $3.49 | 73.5 |
| Command R+ | Cohere | 32768 | $3.96 | 76.3 |
| Llama 3 Hyperbolic Instruct | Hyperbolic | 200000 | $3.79 | 76.2 |
| Llama 3.1 Turbo Base | Together AI | 16384 | $3.30 | 73.0 |
| Phi-4 | Microsoft | 200000 | $3.96 | 75.4 |
| Yi-Large | 01.AI | 32768 | $3.40 | 73.5 |
| Llama 3 Hyperbolic | Hyperbolic | 65536 | $3.86 | 74.5 |
Other benchmarks for Phi-4
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 79.5 | 198 | 67th | |
| GPQA Diamond | 69.4 | 284 | 53th | |
| SWE-bench Verified | 66.5 | 180 | 70th | |
| MATH-500 | 79.0 | 236 | 61th | |
| AIME 2025 | 74.1 | 180 | 70th | |
| LiveCodeBench | 64.7 | 303 | 50th | |
| IFEval | 83.0 | 246 | 59th | |
| TruthfulQA | 76.5 | 295 | 51th | |
| HellaSwag | 86.3 | 206 | 66th | |
| MMMU | 71.2 | 267 | 56th | |
| Arena Elo | 1392.0 | 240 | 60th |
FAQ
What score does Phi-4 get on HumanEval?
Phi-4 scores 79.4 on HumanEval in this index. The benchmark average is 74.0 and the top score is 96.8.
How does Phi-4 rank on HumanEval?
It ranks #253 of 600 models, in the 58th percentile. The leader is GPT-5.2 Pro at 96.8.
Is Phi-4 good at HumanEval?
Yes, relative to the index: it is above the median and inside the top half of scores. The result should be read alongside its price and context window.
How is the HumanEval score calculated?
HumanEval is a coding benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.
What does Phi-4 cost?
Phi-4 costs $3.96 per million input tokens and $20.63 per million output tokens.