Compare / Qwen3 Next 80B A3B Thinking vs Mercury 2
Qwen3 Next 80B A3B Thinking vs Mercury 2
Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 3 sources that measured both models.
Qwen3 Next 80B A3B Thinking or Mercury 2? The short answer
- Mercury 2 is cheaper: $0.38 against $0.41 per million tokens, 9% less.
- Mercury 2 scores higher on the Artificial Analysis Intelligence Index: 13.8 against 11.2.
- On our business benchmarks, Qwen3 Next 80B A3B Thinking ranks higher for writing and sticking to the facts.
- On our business benchmarks, Mercury 2 ranks higher for agents and tool use and reasoning and knowledge.
At a glance
| Qwen3 Next 80B A3B Thinking | Mercury 2 | |
|---|---|---|
| Price per million tokens | $0.15 in · $1.20 out | $0.25 in · $0.75 out |
| Blended (3 in : 1 out) | $0.41 | $0.38 |
| Cheapest host, blended | $0.41 (Google) | – |
| Intelligence Index | 11.2 | 13.8 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 182 | – |
| Context window | 262,144 tokens | 128,000 tokens |
| Weights | Open | 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Qwen3 Next 80B A3B Thinking | Mercury 2 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 137 of 161 | 107 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 122 of 195 | 109 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 142 of 187 | 146 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 64 of 153 | 136 of 153 |
Every shared result
| Benchmark | Metric | Qwen3 Next 80B A3B Thinking | Mercury 2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,367 | 1,340 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,326 | 1,292 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,394 | 1,348 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,359 | 1,327 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,369 | 1,343 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,341 | 1,307 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 17.4 | 31.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 11.2 | 13.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 75.9% | 77.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 12.6% | 17.1% |
| Artificial Analysisreported | IFBench% of instructions | 60.7% | 69.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 63.7% | 43.7% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 6.7% | 27.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 9.8% | 26.5% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 6.2% | 9.5% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 41.5% | 70.8% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 94.4% | 100.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 9.3% | 12.3% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Qwen3 Next 80B A3B Thinking better than Mercury 2?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3 Next 80B A3B Thinking ranks higher for writing and sticking to the facts; Mercury 2 ranks higher for agents and tool use and reasoning and knowledge.
Which is cheaper, Qwen3 Next 80B A3B Thinking or Mercury 2?
Mercury 2 costs $0.38 per million tokens (three input to one output), against $0.41 for Qwen3 Next 80B A3B Thinking.
Run Qwen3 Next 80B A3B Thinking and Mercury 2 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.