Compare / Qwen3-30B-A3B-Instruct-2507 vs gpt-oss-120b

Qwen3-30B-A3B-Instruct-2507 vs gpt-oss-120b

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

AlibabaQwen3-30B-A3B-Instruct-2507 Released 29 Jul 2025 · $0.090 in · $0.30 out
OpenAIgpt-oss-120b Released 5 Aug 2025 · $0.15 in · $0.60 out
Qwen3-30B-A3B-Instruct-2507 wins 8gpt-oss-120b wins 8

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 14 October 2026 (catalogue release 2026-10-14-7d7cf32c3f6d). See also Alibaba vs OpenAI, every model from both labs.

Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b? The short answer

Pick gpt-oss-120b if quality matters most: it scores higher (Intelligence Index 11.6 against 7.5). Pick Qwen3-30B-A3B-Instruct-2507 if cost matters more: it costs 46% less per token.

  • Qwen3-30B-A3B-Instruct-2507 is cheaper: $0.14 against $0.26 per million tokens, 46% less.
  • gpt-oss-120b scores higher on the Artificial Analysis Intelligence Index: 11.6 against 7.5.
  • gpt-oss-120b is newer: released 5 Aug 2025, against 29 Jul 2025 for Qwen3-30B-A3B-Instruct-2507.
  • On third-party benchmarks, on the results both models have: gpt-oss-120b does better for reasoning and knowledge.

Head to head

7.5
Intelligence Index
11.6
$0.14
Price per million tokens, blendedlower is better
$0.26
262,144
Context window, tokens
131,072

Every fact side by side

Qwen3-30B-A3B-Instruct-2507gpt-oss-120b
Price per million tokens$0.090 in · $0.30 out$0.15 in · $0.60 out
Blended (3 in : 1 out)$0.14$0.26
Cheapest host, blended$0.084 (StreamLake)$0.065 (CoreWeave, FP4)
Intelligence Index7.511.6
Spring Prompt overall––
Output speed, tokens a second–242
Context window262,144 tokens131,072 tokens
Released29 Jul 20255 Aug 2025 (newer)
WeightsOpenOpen
Developer based inChinathe 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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 77 of 166 122 of 166
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 49 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 161 of 200 116 of 200
WritingWhat people prefer in blind comparisons, and judged writing quality 141 of 189 134 of 189
Sticking to the factsSummarising without inventing things, and factual answers not measured 140 of 153

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.

MeasureQwen3-30B-A3B-Instruct-2507gpt-oss-120b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 162 · 187 of 387 measured 1,383 1,352
Business, management and finance · TextArena rating, higher is better 144 · 183 of 380 measured 1,397 1,352
Creative writing · TextArena rating, higher is better 186 · 238 of 385 measured 1,319 1,278
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 210 · 158 of 244 measured 7.5 11.6high reasoning
GPQA Diamond% of questions, higher is better 172 · 118 of 231 measured 65.9% 78.2%high reasoning
Humanity's Last Exam% of questions, higher is better 174 · 111 of 243 measured 6.9% 19.6%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 163 · 116 of 230 measured 27.9 38.5medium reasoning
Requested-length error · UGI% off the requested word count, lower is better 57 · 224 of 230 measured 13.0% 107.0%medium reasoning
Style adherence · UGIscore from 0 to 1, higher is better 187 · 217 of 230 measured 0.31 0.29medium reasoning
Show all 16 results (7 more)
MeasureQwen3-30B-A3B-Instruct-2507gpt-oss-120b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 163 · 188 of 338 measured 1,395 1,357
Instruction following · TextArena rating, higher is better 164 · 204 of 387 measured 1,367 1,323
Writing, literature and language · TextArena rating, higher is better 176 · 215 of 386 measured 1,342 1,309
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 168 · 58 of 195 measured 33.1% 69.0%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 192 · 153 of 234 measured 26.3% 52.0%high reasoning
Terminal-Bench Hard% of tasks, higher is better 147 · 84 of 190 measured 6.1% 23.5%high reasoning
τ²-bench telecom% of tasks, higher is better 185 · 86 of 193 measured 10.2% 65.8%high reasoning

Quick answers

Is Qwen3-30B-A3B-Instruct-2507 better than gpt-oss-120b?

Pick gpt-oss-120b if quality matters most: it scores higher (Intelligence Index 11.6 against 7.5). Pick Qwen3-30B-A3B-Instruct-2507 if cost matters more: it costs 46% less per token.

Which is cheaper, Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b?

Qwen3-30B-A3B-Instruct-2507 is cheaper: $0.14 against $0.26 per million tokens, 46% less.

Which is better for agents and tool use, Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b?

Qwen3-30B-A3B-Instruct-2507 ranks 77 of 166 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 122 for gpt-oss-120b.

Which is better for reasoning and knowledge, Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b?

gpt-oss-120b ranks 116 of 200 models on sale for hard questions across science, maths and general knowledge, against 161 for Qwen3-30B-A3B-Instruct-2507.

Which is better for writing, Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b?

gpt-oss-120b ranks 134 of 189 models on sale for what people prefer in blind comparisons, and judged writing quality, against 141 for Qwen3-30B-A3B-Instruct-2507.

Which has the bigger context window, Qwen3-30B-A3B-Instruct-2507 or gpt-oss-120b?

Qwen3-30B-A3B-Instruct-2507: 262,144 tokens, against 131,072 for gpt-oss-120b.

Run Qwen3-30B-A3B-Instruct-2507 and gpt-oss-120b on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us