Compare / Qwen3.5-9B vs Gemini 2.5 Pro
Qwen3.5-9B vs Gemini 2.5 Pro
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 2 sources that measured both models.
Of the 15 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Alibaba vs Google, every model from both labs.
Qwen3.5-9B or Gemini 2.5 Pro? The short answer
Pick Gemini 2.5 Pro if quality matters most: it scores higher (Intelligence Index 16.1 against 13.3). Pick Qwen3.5-9B if cost matters more: it costs 31 times less per token.
- Qwen3.5-9B is cheaper: $0.11 against $3.44 per million tokens, 31 times less.
- Gemini 2.5 Pro scores higher on the Artificial Analysis Intelligence Index: 16.1 against 13.3.
- Qwen3.5-9B is newer: released 2 Mar 2026, against 25 Mar 2025 for Gemini 2.5 Pro.
- On third-party benchmarks, on the results both models have: Qwen3.5-9B does better for agents and tool use; Gemini 2.5 Pro for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Qwen3.5-9B | Gemini 2.5 Pro | |
|---|---|---|
| Price per million tokens | $0.10 in · $0.15 out | $1.25 in · $10.00 out |
| Blended (3 in : 1 out) | $0.11 | $3.44 |
| Cheapest host, blended | $0.092 (Darkbloom, FP4) | – |
| Cached input, per million | – | $0.12 cached input |
| Intelligence Index | 13.3 | 16.1 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 110 | – |
| Context window | 262,144 tokens | 1,048,576 tokens |
| Released | 2 Mar 2026 (newer) | 25 Mar 2025 |
| 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 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 | Qwen3.5-9B | Gemini 2.5 Pro |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 145 · 128 of 249 measured | 13.3no reasoning | 16.1 |
| GPQA Diamond% of questions, higher is better 109 · 87 of 232 measured | 80.6% | 84.4% |
| Humanity's Last Exam% of questions, higher is better 134 · 108 of 250 measured | 14.9% | 22.5% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 113 · 28 of 230 measured | 39.5think-prefill reasoning | 65.2 |
| Requested-length error · UGI% off the requested word count, lower is better 69 · 99 of 230 measured | 15.0%think-prefill reasoning | 19.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 173 · 16 of 230 measured | 0.32no reasoning | 0.40 |
Show all 15 results (9 more)
| Measure | Qwen3.5-9B | Gemini 2.5 Pro |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 9 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 84 · 85 of 131 measured | 29.2% | 28.5% |
| Terminal-Bench 4.0% of tasks, higher is better 65 · 72 of 120 measured | 0.5% | 0.0% |
| τ-bench banking% of tasks, higher is better 90 · 79 of 121 measured | 7.0% | 9.7% |
| Artificial Analysis Coding Indexindex score, higher is better 87 · 81 of 130 measured | 28.7 | 33.3 |
| IFBench% of instructions, higher is better 68 · 108 of 195 measured | 66.7% | 48.7% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 116 · 123 of 241 measured | 70.0% | 69.0% |
| SciCode% of problems, higher is better 110 · 69 of 121 measured | 29.5% | 46.3% |
| Terminal-Bench Hard% of tasks, higher is better 80 · 74 of 190 measured | 24.2% | 26.5% |
| τ²-bench telecom% of tasks, higher is better 51 · 99 of 193 measured | 86.8% | 54.1% |
Compare them with other models
Quick answers
Is Qwen3.5-9B better than Gemini 2.5 Pro?
Pick Gemini 2.5 Pro if quality matters most: it scores higher (Intelligence Index 16.1 against 13.3). Pick Qwen3.5-9B if cost matters more: it costs 31 times less per token.
Which is cheaper, Qwen3.5-9B or Gemini 2.5 Pro?
Qwen3.5-9B is cheaper: $0.11 against $3.44 per million tokens, 31 times less.
Which is better for agents and tool use, Qwen3.5-9B or Gemini 2.5 Pro?
Qwen3.5-9B ranks 111 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 118 for Gemini 2.5 Pro.
Which is better for reasoning and knowledge, Qwen3.5-9B or Gemini 2.5 Pro?
Gemini 2.5 Pro ranks 102 of 187 models on sale for hard questions across science, maths and general knowledge, against 116 for Qwen3.5-9B.
Which is better for writing, Qwen3.5-9B or Gemini 2.5 Pro?
Gemini 2.5 Pro ranks 44 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 112 for Qwen3.5-9B.
Which has the bigger context window, Qwen3.5-9B or Gemini 2.5 Pro?
Gemini 2.5 Pro: 1,048,576 tokens, against 262,144 for Qwen3.5-9B.
Run Qwen3.5-9B and Gemini 2.5 Pro on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.