Compare / Mistral Small 4 vs gpt-oss-20b
Mistral Small 4 vs gpt-oss-20b
Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 2 sources that measured both models.
Of the 17 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 Small 4 or gpt-oss-20b? The short answer
They score about the same, so pick gpt-oss-20b: it costs 4.6 times less per token.
- gpt-oss-20b is cheaper: $0.058 against $0.26 per million tokens, 4.6 times less.
- Mistral Small 4 scores higher on the Artificial Analysis Intelligence Index: 11.3 against 10.0.
- gpt-oss-20b writes faster: 277 tokens a second against 176.
- Mistral Small 4 is newer: released 16 Mar 2026, against 5 Aug 2025 for gpt-oss-20b.
- On third-party benchmarks, on the results both models have: Mistral Small 4 does better for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Mistral Small 4 | gpt-oss-20b | |
|---|---|---|
| Price per million tokens | $0.15 in · $0.60 out | $0.030 in · $0.14 out |
| Blended (3 in : 1 out) | $0.26 | $0.058 |
| Cheapest host, blended | $0.26 (Mistral) | $0.022 (PrimeIntellect, FP4) |
| Cached input, per million | $0.015 cached input | – |
| Intelligence Index | 11.3 | 10.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 176 | 277 |
| Context window | 262,144 tokens | 131,072 tokens |
| Released | 16 Mar 2026 (newer) | 5 Aug 2025 |
| Weights | Open | Open |
| Developer based in | France | 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 | Mistral Small 4 | gpt-oss-20b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 164 · 176 of 249 measured | 11.3 | 10.0low reasoning |
| GPQA Diamond% of questions, higher is better 130 · 159 of 232 measured | 76.9% | 68.8%high reasoning |
| Humanity's Last Exam% of questions, higher is better 164 · 153 of 250 measured | 9.9% | 11.0%high reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 110 · 182 of 230 measured | 40.3no reasoning | 24.6low reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 129 · 221 of 230 measured | 22.0%no reasoning | 98.0%low reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 192 · 187 of 230 measured | 0.31high reasoning | 0.31medium reasoning |
Show all 17 results (11 more)
| Measure | Mistral Small 4 | gpt-oss-20b |
|---|---|---|
| Artificial Analysis reported by Artificial Analysis · 11 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 91 · 97 of 131 measured | 21.0% | 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 107 · 90 of 121 measured | 4.9% | 7.0%high reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 88 · 100 of 130 measured | 26.6 | 20.7high reasoning |
| IFBench% of instructions, higher is better 109 · 69 of 195 measured | 48.2% | 65.1%high reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 165 · 184 of 241 measured | 49.7% | 34.7%high reasoning |
| Output speedtokens per second, higher is better 19 · 6 of 78 measured | 176 | 277low reasoning |
| SciCode% of problems, higher is better 91 · 90 of 121 measured | 38.8% | 38.9%high reasoning |
| Terminal-Bench Hard% of tasks, higher is better 100 · 127 of 190 measured | 17.4% | 10.6%high reasoning |
| Time to first answer tokenseconds, lower is better 9 · 44 of 78 measured | 0.57no reasoning | 7.62low reasoning |
| τ²-bench telecom% of tasks, higher is better 114 · 96 of 193 measured | 41.2% | 60.2%high reasoning |
Compare them with other models
Quick answers
Is Mistral Small 4 better than gpt-oss-20b?
They score about the same, so pick gpt-oss-20b: it costs 4.6 times less per token.
Which is cheaper, Mistral Small 4 or gpt-oss-20b?
gpt-oss-20b is cheaper: $0.058 against $0.26 per million tokens, 4.6 times less.
Which is faster, Mistral Small 4 or gpt-oss-20b?
gpt-oss-20b writes about 277 tokens a second on its usual API, against 176 for Mistral Small 4 (Artificial Analysis).
Which is better for agents and tool use, Mistral Small 4 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 133 for Mistral Small 4.
Which is better for reasoning and knowledge, Mistral Small 4 or gpt-oss-20b?
Mistral Small 4 ranks 127 of 187 models on sale for hard questions across science, maths and general knowledge, against 132 for gpt-oss-20b.
Which is better for writing, Mistral Small 4 or gpt-oss-20b?
Mistral Small 4 ranks 111 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 Small 4 or gpt-oss-20b?
Mistral Small 4: 262,144 tokens, against 131,072 for gpt-oss-20b.
Run Mistral Small 4 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.