Compare / Qwen3.6-Max-Preview vs Claude Haiku 4.5
Qwen3.6-Max-Preview vs Claude Haiku 4.5
Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 4 sources that measured both models.
Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5). See also Alibaba vs Anthropic, every model from both labs.
Qwen3.6-Max-Preview or Claude Haiku 4.5? The short answer
Pick Qwen3.6-Max-Preview: it scores higher (Intelligence Index 28.4 against 16.9) at about the same price.
- They cost about the same: $2.31 and $2.00 per million tokens (three input to one output).
- Qwen3.6-Max-Preview scores higher on the Artificial Analysis Intelligence Index: 28.4 against 16.9.
- Qwen3.6-Max-Preview is newer: released 20 Apr 2026, against 15 Oct 2025 for Claude Haiku 4.5.
- On third-party benchmarks, on the results both models have: Qwen3.6-Max-Preview does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3.6-Max-Preview | Claude Haiku 4.5 | |
|---|---|---|
| Price per million tokens | $1.03 in · $6.16 out | $1.00 in · $5.00 out |
| Blended (3 in : 1 out) | $2.31 | $2.00 |
| Cheapest host, blended | – | $2.00 (Amazon Bedrock) |
| Cached input, per million | – | $0.10 cached input |
| Intelligence Index | 28.4 | 16.9 |
| Spring Prompt overall | – | 7 |
| Output speed, tokens a second | – | 97 |
| Context window | 262,144 tokens | 200,000 tokens |
| Released | 20 Apr 2026 (newer) | 15 Oct 2025 |
| Weights | Closed | Closed |
| Developer based in | China | the US |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Qwen3.6-Max-Preview | Claude Haiku 4.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 51 · 121 of 387 measured | 1,460 | 1,414 |
| Overall · Text factualityArena rating, higher is better 51 · 118 of 163 measured | 1,453 | 1,418 |
| Business, management and finance · TextArena rating, higher is better 64 · 109 of 380 measured | 1,451 | 1,420 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 57 · 116 of 243 measured | 28.4 | 16.9thinking reasoning |
| GPQA Diamond% of questions, higher is better 55 · 163 of 231 measured | 88.8% | 67.2%thinking reasoning |
| Humanity's Last Exam% of questions, higher is better 70 · 149 of 242 measured | 30.8% | 10.4%thinking reasoning |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 21 · 69 of 76 measured | 52.0% | 13.2% |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 31 · 49 of 58 measured | $4,254 | $458.89 |
Show all 16 results (8 more)
| Measure | Qwen3.6-Max-Preview | Claude Haiku 4.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 50 · 112 of 385 measured | 1,437 | 1,388 |
| Expert prompts · TextArena rating, higher is better 36 · 97 of 338 measured | 1,500 | 1,451 |
| Instruction following · TextArena rating, higher is better 56 · 101 of 387 measured | 1,450 | 1,415 |
| Writing, literature and language · TextArena rating, higher is better 50 · 106 of 386 measured | 1,446 | 1,400 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 14 · 92 of 195 measured | 76.6% | 54.3%thinking reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 33 · 82 of 233 measured | 80.7% | 74.3%thinking reasoning |
| Terminal-Bench Hard% of tasks, higher is better 23 · 72 of 190 measured | 43.9% | 27.3%no reasoning |
| τ²-bench telecom% of tasks, higher is better 12 · 98 of 193 measured | 95.9% | 54.7%thinking reasoning |
Compare them with other models
Quick answers
Is Qwen3.6-Max-Preview better than Claude Haiku 4.5?
Pick Qwen3.6-Max-Preview: it scores higher (Intelligence Index 28.4 against 16.9) at about the same price.
Which is cheaper, Qwen3.6-Max-Preview or Claude Haiku 4.5?
They cost about the same: $2.31 and $2.00 per million tokens (three input to one output).
Which is better for agents and tool use, Qwen3.6-Max-Preview or Claude Haiku 4.5?
Qwen3.6-Max-Preview ranks 81 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 91 for Claude Haiku 4.5.
Which is better for reasoning and knowledge, Qwen3.6-Max-Preview or Claude Haiku 4.5?
Qwen3.6-Max-Preview ranks 59 of 198 models on sale for hard questions across science, maths and general knowledge, against 127 for Claude Haiku 4.5.
Which is better for writing, Qwen3.6-Max-Preview or Claude Haiku 4.5?
Qwen3.6-Max-Preview ranks 41 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 87 for Claude Haiku 4.5.
Which is better for sticking to the facts, Qwen3.6-Max-Preview or Claude Haiku 4.5?
Qwen3.6-Max-Preview ranks 45 of 152 models on sale for summarising without inventing things, and factual answers, against 117 for Claude Haiku 4.5.
Which has the bigger context window, Qwen3.6-Max-Preview or Claude Haiku 4.5?
Qwen3.6-Max-Preview: 262,144 tokens, against 200,000 for Claude Haiku 4.5.
Run Qwen3.6-Max-Preview and Claude Haiku 4.5 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.