Claude Haiku 4.5 Nano on HellaSwag: score, rank and what it means
Claude Haiku 4.5 Nano scores 80.5 on HellaSwag, placing it #378 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 Claude Haiku 4.5 Nano 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, Claude Haiku 4.5 Nano sits at #378 of 600. The leader, GPT-5.2 Max, scores 96.1, so the gap to the top is 15.6 points. The median model in this index scores 83.6, which puts Claude Haiku 4.5 Nano below the midpoint.
Anthropic models average 89.3 on this benchmark. Claude Haiku 4.5 Nano is 8.8 points below that provider line, so it is a weaker result than the average Anthropic model.
Among mid-range models, the average is 79.8. Claude Haiku 4.5 Nano is 0.7 points above that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 80.5 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 $6.47 per million input tokens, Claude Haiku 4.5 Nano is above 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 |
|---|---|---|---|---|
| DBRX Chat | Databricks | 65536 | $3.07 | 71.7 |
| Gemini 2.5 Pro Nano | Google DeepMind | 32768 | $7.28 | 69.2 |
| Sonar Pro Mini | Perplexity | 8192 | $8.02 | 70.3 |
| Arctic | Snowflake | 8192 | $2.72 | 68.8 |
| Claude Haiku 4.5 Nano | Anthropic | 8192 | $6.47 | 68.7 |
| Arctic Base | Snowflake | 32768 | $2.27 | 67.5 |
| Firesearch Turbo | Fireworks AI | 16384 | $7.58 | 69.3 |
Other benchmarks for Claude Haiku 4.5 Nano
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 73.9 | 355 | 41th | |
| GPQA Diamond | 64.5 | 369 | 39th | |
| SWE-bench Verified | 56.9 | 367 | 39th | |
| HumanEval | 71.0 | 388 | 35th | |
| MATH-500 | 71.8 | 369 | 39th | |
| AIME 2025 | 63.5 | 361 | 40th | |
| LiveCodeBench | 59.8 | 369 | 39th | |
| IFEval | 78.2 | 363 | 40th | |
| TruthfulQA | 71.6 | 385 | 36th | |
| MMMU | 64.3 | 386 | 36th | |
| Arena Elo | 1332.1 | 385 | 36th |
FAQ
What score does Claude Haiku 4.5 Nano get on HellaSwag?
Claude Haiku 4.5 Nano scores 80.5 on HellaSwag in this index. The benchmark average is 81.4 and the top score is 96.1.
How does Claude Haiku 4.5 Nano rank on HellaSwag?
It ranks #378 of 600 models, in the 37th percentile. The leader is GPT-5.2 Max at 96.1.
Is Claude Haiku 4.5 Nano good at HellaSwag?
It is below the median for this benchmark, so test it carefully before relying on it for this capability. 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 Claude Haiku 4.5 Nano cost?
Claude Haiku 4.5 Nano costs $6.47 per million input tokens and $27.98 per million output tokens.