Compare / Mistral Large 3 vs gpt-oss-20b

Mistral Large 3 vs gpt-oss-20b

Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.

Mistral AIMistral Large 3 Released 2 Dec 2025 · $0.50 in · $1.50 out
OpenAIgpt-oss-20b Released 5 Aug 2025 · $0.030 in · $0.14 out
Mistral Large 3 wins 111 too close to callgpt-oss-20b wins 9

Of the 21 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 Mistral AI vs OpenAI, every model from both labs.

Mistral Large 3 or gpt-oss-20b? The short answer

They score about the same, so pick gpt-oss-20b: it costs 13 times less per token.

  • gpt-oss-20b is cheaper: $0.058 against $0.75 per million tokens, 13 times less.
  • They score about the same on the Artificial Analysis Intelligence Index (9.3 and 10.0).
  • Mistral Large 3 is newer: released 2 Dec 2025, against 5 Aug 2025 for gpt-oss-20b.
  • On third-party benchmarks, on the results both models have: Mistral Large 3 does better for writing; gpt-oss-20b for agents and tool use and reasoning and knowledge.

Head to head

9.3
Intelligence Index
10.0
$0.75
Price per million tokens, blendedlower is better
$0.058
262,144
Context window, tokens
131,072

Every fact side by side

Mistral Large 3gpt-oss-20b
Price per million tokens$0.50 in · $1.50 out$0.030 in · $0.14 out
Blended (3 in : 1 out)$0.75$0.058
Cheapest host, blended$0.75 (Mistral)$0.022 (PrimeIntellect, FP4)
Cached input, per million$0.050 cached input–
Intelligence Index9.310.0
Spring Prompt overall––
Output speed, tokens a second–277
Context window262,144 tokens131,072 tokens
Released2 Dec 2025 (newer)5 Aug 2025
WeightsClosedOpen
Developer based inFrancethe 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 136 of 159 130 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 150 of 187 132 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 95 of 169 155 of 169
Sticking to the factsSummarising without inventing things, and factual answers 115 of 139 not measured

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.

MeasureMistral Large 3gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 120 · 237 of 387 measured 1,414 1,318
Business, management and finance · TextArena rating, higher is better 124 · 213 of 380 measured 1,410 1,323
Creative writing · TextArena rating, higher is better 126 · 275 of 385 measured 1,374 1,240
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 185 · 176 of 249 measured 9.3 10.0low reasoning
GPQA Diamond% of questions, higher is better 162 · 159 of 232 measured 68.0% 68.8%high reasoning
Humanity's Last Exam% of questions, higher is better 221 · 153 of 250 measured 4.2% 11.0%high reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 104 · 182 of 230 measured 41.6no reasoning 24.6low reasoning
Requested-length error · UGI% off the requested word count, lower is better 69 · 221 of 230 measured 15.0%no reasoning 98.0%low reasoning
Style adherence · UGIscore from 0 to 1, higher is better 35 · 187 of 230 measured 0.38no reasoning 0.31medium reasoning
Show all 21 results (12 more)
MeasureMistral Large 3gpt-oss-20b
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 129 · 220 of 338 measured 1,427 1,314
Instruction following · TextArena rating, higher is better 123 · 257 of 387 measured 1,400 1,281
Writing, literature and language · TextArena rating, higher is better 121 · 261 of 386 measured 1,389 1,275
Artificial Analysis reported by Artificial Analysis · 9 results
Terminal-Bench 2.1% of tasks, higher is better 102 · 97 of 131 measured 12.0% 13.9%high reasoning
Terminal-Bench 4.0% of tasks, higher is better 72 · 72 of 120 measured 0.0% 0.0%high reasoning
τ-bench banking% of tasks, higher is better 98 · 90 of 121 measured 5.8% 7.0%high reasoning
Artificial Analysis Coding Indexindex score, higher is better 103 · 100 of 130 measured 20.1 20.7high reasoning
IFBench% of instructions, higher is better 156 · 69 of 195 measured 36.2% 65.1%high reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 183 · 184 of 241 measured 36.0% 34.7%high reasoning
SciCode% of problems, higher is better 95 · 90 of 121 measured 36.6% 38.9%high reasoning
Terminal-Bench Hard% of tasks, higher is better 107 · 127 of 190 measured 15.9% 10.6%high reasoning
τ²-bench telecom% of tasks, higher is better 155 · 96 of 193 measured 24.6% 60.2%high reasoning

Quick answers

Is Mistral Large 3 better than gpt-oss-20b?

They score about the same, so pick gpt-oss-20b: it costs 13 times less per token.

Which is cheaper, Mistral Large 3 or gpt-oss-20b?

gpt-oss-20b is cheaper: $0.058 against $0.75 per million tokens, 13 times less.

Which is better for agents and tool use, Mistral Large 3 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 136 for Mistral Large 3.

Which is better for reasoning and knowledge, Mistral Large 3 or gpt-oss-20b?

gpt-oss-20b ranks 132 of 187 models on sale for hard questions across science, maths and general knowledge, against 150 for Mistral Large 3.

Which is better for writing, Mistral Large 3 or gpt-oss-20b?

Mistral Large 3 ranks 95 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, Mistral Large 3 or gpt-oss-20b?

Mistral Large 3: 262,144 tokens, against 131,072 for gpt-oss-20b.

Run Mistral Large 3 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.