Claude Haiku 4.5 Vision on HellaSwag: score, rank and what it means
Claude Haiku 4.5 Vision scores 88.6 on HellaSwag, placing it #123 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 Vision 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 Vision sits at #123 of 600. The leader, GPT-5.2 Max, scores 96.1, so the gap to the top is 7.5 points. The median model in this index scores 83.6, which puts Claude Haiku 4.5 Vision above the midpoint.
Anthropic models average 89.3 on this benchmark. Claude Haiku 4.5 Vision is 0.7 points below that provider line, so it is a weaker result than the average Anthropic model.
Among multimodal models, the average is 86.8. Claude Haiku 4.5 Vision is 1.8 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 88.6 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 $13.01 per million input tokens, Claude Haiku 4.5 Vision 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 |
|---|---|---|---|---|
| Llama 4 Maverick Chat | Meta AI | 128000 | $5.09 | 79.7 |
| ERNIE 4.0 Max | Baidu | 32768 | $12.40 | 78.9 |
| Reka Core Pro | Reka AI | 65536 | $13.44 | 79.9 |
| Sonar Pro Pro | Perplexity | 200000 | $13.59 | 79.7 |
| Claude Haiku 4.5 Vision | Anthropic | 128000 | $13.01 | 79.2 |
| Kimi K2 Base | Moonshot AI | 65536 | $4.82 | 79.2 |
| MiniMax-M2 Instruct | MiniMax | 128000 | $5.11 | 79.4 |
Other benchmarks for Claude Haiku 4.5 Vision
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 82.7 | 108 | 82th | |
| GPQA Diamond | 73.6 | 181 | 70th | |
| SWE-bench Verified | 67.0 | 168 | 72th | |
| HumanEval | 85.0 | 114 | 81th | |
| MATH-500 | 80.6 | 197 | 67th | |
| AIME 2025 | 75.8 | 144 | 76th | |
| LiveCodeBench | 70.7 | 177 | 71th | |
| IFEval | 86.0 | 154 | 74th | |
| TruthfulQA | 82.8 | 109 | 82th | |
| MMMU | 78.2 | 89 | 85th | |
| Arena Elo | 1413.3 | 176 | 71th |
FAQ
What score does Claude Haiku 4.5 Vision get on HellaSwag?
Claude Haiku 4.5 Vision scores 88.6 on HellaSwag in this index. The benchmark average is 81.4 and the top score is 96.1.
How does Claude Haiku 4.5 Vision rank on HellaSwag?
It ranks #123 of 600 models, in the 80th percentile. The leader is GPT-5.2 Max at 96.1.
Is Claude Haiku 4.5 Vision 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 Claude Haiku 4.5 Vision cost?
Claude Haiku 4.5 Vision costs $13.01 per million input tokens and $53.29 per million output tokens.