Compare / Qwen3-Coder-480B-A35B vs gpt-oss-20b
Qwen3-Coder-480B-A35B vs gpt-oss-20b
Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.
Of the 13 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 OpenAI, every model from both labs.
Qwen3-Coder-480B-A35B or gpt-oss-20b? The short answer
They score about the same, so pick gpt-oss-20b: it costs 8.3 times less per token.
- gpt-oss-20b is cheaper: $0.058 against $0.47 per million tokens, 8.3 times less.
- Qwen3-Coder-480B-A35B scores higher on the Artificial Analysis Intelligence Index: 11.9 against 10.0.
- gpt-oss-20b is newer: released 5 Aug 2025, against 31 Jul 2025 for Qwen3-Coder-480B-A35B.
- On third-party benchmarks, on the results both models have: Qwen3-Coder-480B-A35B does better for writing; gpt-oss-20b for reasoning and knowledge.
Head to head
Every fact side by side
| Qwen3-Coder-480B-A35B | gpt-oss-20b | |
|---|---|---|
| Price per million tokens | $0.30 in · $1.00 out | $0.030 in · $0.14 out |
| Blended (3 in : 1 out) | $0.47 | $0.058 |
| Cheapest host, blended | $0.47 (DeepInfra, FP4) | $0.022 (PrimeIntellect, FP4) |
| Intelligence Index | 11.9 | 10.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | 277 |
| Context window | 262,144 tokens | 131,072 tokens |
| Released | 31 Jul 2025 | 5 Aug 2025 (newer) |
| Weights | Open | Open |
| 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.
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-Coder-480B-A35B | gpt-oss-20b |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 156 · 237 of 387 measured | 1,387 | 1,318 |
| Business, management and finance · TextArena rating, higher is better 148 · 213 of 380 measured | 1,391 | 1,323 |
| Creative writing · TextArena rating, higher is better 141 · 275 of 385 measured | 1,363 | 1,240 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 159 · 176 of 249 measured | 11.9 | 10.0low reasoning |
| GPQA Diamond% of questions, higher is better 179 · 159 of 232 measured | 61.8% | 68.8%high reasoning |
| Humanity's Last Exam% of questions, higher is better 210 · 153 of 250 measured | 4.5% | 11.0%high reasoning |
Show all 13 results (7 more)
| Measure | Qwen3-Coder-480B-A35B | gpt-oss-20b |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 174 · 220 of 338 measured | 1,379 | 1,314 |
| Instruction following · TextArena rating, higher is better 144 · 257 of 387 measured | 1,384 | 1,281 |
| Writing, literature and language · TextArena rating, higher is better 150 · 261 of 386 measured | 1,366 | 1,275 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 133 · 69 of 195 measured | 40.5% | 65.1%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 169 · 184 of 241 measured | 45.7% | 34.7%high reasoning |
| Terminal-Bench Hard% of tasks, higher is better 94 · 127 of 190 measured | 18.9% | 10.6%high reasoning |
| τ²-bench telecom% of tasks, higher is better 110 · 96 of 193 measured | 43.6% | 60.2%high reasoning |
Compare them with other models
Quick answers
Is Qwen3-Coder-480B-A35B better than gpt-oss-20b?
They score about the same, so pick gpt-oss-20b: it costs 8.3 times less per token.
Which is cheaper, Qwen3-Coder-480B-A35B or gpt-oss-20b?
gpt-oss-20b is cheaper: $0.058 against $0.47 per million tokens, 8.3 times less.
Which is better for agents and tool use, Qwen3-Coder-480B-A35B or gpt-oss-20b?
gpt-oss-20b ranks 130 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 157 for Qwen3-Coder-480B-A35B.
Which is better for reasoning and knowledge, Qwen3-Coder-480B-A35B or gpt-oss-20b?
gpt-oss-20b ranks 132 of 187 models on sale for hard questions across science, maths and general knowledge, against 145 for Qwen3-Coder-480B-A35B.
Which is better for writing, Qwen3-Coder-480B-A35B or gpt-oss-20b?
Qwen3-Coder-480B-A35B ranks 115 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 155 for gpt-oss-20b.
Which has the bigger context window, Qwen3-Coder-480B-A35B or gpt-oss-20b?
Qwen3-Coder-480B-A35B: 262,144 tokens, against 131,072 for gpt-oss-20b.
Run Qwen3-Coder-480B-A35B and gpt-oss-20b 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.