Phi-4 on HellaSwag: score, rank and what it means
Phi-4 scores 86.3 on HellaSwag, placing it #206 of 600 models in the index. The benchmark average is 81.4 and the leader is GPT-5.2 Max at 96.1.
Score distribution
The chart shows the top 10 models on HellaSwag, with Phi-4 highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 2 | GPT-5.2 Turbo | OpenAI | 1000000 | $20.73 | 87.4 |
| 3 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 4 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 5 | Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
| 6 | Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| 7 | GPT-5.2 Vision | OpenAI | 1000000 | $19.03 | 87.4 |
| 8 | Gemini 3 Pro Turbo | Google DeepMind | 400000 | $19.62 | 86.4 |
| 9 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 10 | o4 Pro | OpenAI | 1000000 | $19.37 | 87.3 |
What this score means
On HellaSwag, Phi-4 sits at #206 of 600. The leader, GPT-5.2 Max, scores 96.1, so the gap to the top is 9.8 points. The median model in this index scores 83.6, which puts Phi-4 above the midpoint.
Microsoft models average 76.8 on this benchmark. Phi-4 is 9.5 points above that provider line, so it is a stronger result than the average Microsoft model.
Among multimodal models, the average is 86.8. Phi-4 is 0.5 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 86.3 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 HellaSwag. 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 |
|---|---|---|---|---|
| Reka Core Max | Reka AI | 128000 | $13.41 | 79.3 |
| o3 Mini | OpenAI | 128000 | $10.68 | 76.2 |
| Codestral Chat | Mistral AI | 32768 | $3.89 | 75.8 |
| Llama 3 Replicate Instruct | Replicate | 128000 | $3.71 | 75.1 |
| Phi-4 | Microsoft | 200000 | $3.96 | 75.4 |
| Reka Core Turbo | Reka AI | 32768 | $12.58 | 78.4 |
| Llama 3 Lambda Chat | Lambda | 32768 | $3.73 | 74.7 |
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 | |
| HumanEval | 79.4 | 253 | 58th | |
| 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 | |
| MMMU | 71.2 | 267 | 56th | |
| Arena Elo | 1392.0 | 240 | 60th |
FAQ
What score does Phi-4 get on HellaSwag?
Phi-4 scores 86.3 on HellaSwag in this index. The benchmark average is 81.4 and the top score is 96.1.
How does Phi-4 rank on HellaSwag?
It ranks #206 of 600 models, in the 66th percentile. The leader is GPT-5.2 Max at 96.1.
Is Phi-4 good at HellaSwag?
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 HellaSwag score calculated?
HellaSwag is a commonsense 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.