Models / gpt-oss-120b
gpt-oss-120b
gpt-oss-120b trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.20.
Results 16 Nov 2026 · 40 results · 6 sources
Test gpt-oss-120b on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.10 in · $0.50 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices - Speed
- 259 tokens a second; on its test prompt the answer starts after 8.2 s, thinking time included
Artificial Analysis, on its usual API, at high reasoning; 258–259 across 2 settings - Intelligence Index
- 11.6
Artificial Analysis, at high reasoning; 10.2–11.6 across 2 settings - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- OpenAI, based in the US
Weights published - Released
- 5 Aug 2025
131,072 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 129th of 185Claude Opus 5.5 | – | $0.20 blended, 18th percentilecheapest: Mistral Nemo | 7th of 65Nemotron 3.5 Super VL |
| Models priced under $0.25 per million tokens | 15th of 41Claude Haiku 5.5 | – | sets this group | 4th of 19Nemotron 3.5 Super VL |
| Models with similar intelligence | sets this group | – | $0.20 blended, 22nd percentilecheapest: gpt-oss-20b | 2nd of 13gpt-oss-20b |
| Models writing 200 or more tokens a second | 10th of 14Muse Spark 1.3 | – | $0.20 blended, 31st percentilecheapest: gpt-oss-20b | sets this group |
| Models from developers based in the US | 68th of 92Claude Opus 5.5 | – | $0.20 blended, 18th percentilecheapest: Gemma 3 4B | 5th of 33Nemotron 3.5 Super VL |
| Open-weights models | 61st of 104MiMo-V2.6-Pro | – | $0.20 blended, 26th percentilecheapest: Mistral Nemo | 5th of 43Nemotron 3.5 Super VL |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | gpt-oss-120b | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported | 0.0% | 67th of 107 | Kimi K3.1 Pro 67.2% |
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 26.2% | 79th of 107 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 12.8% | 63rd of 104 | Grok 4.6 50.7% |
| Vending-Bench 2Vending-Bench 2: money after a year · reported | $-21.53 | 51st of 53 | GPT-6 Astra $15,515 |
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
| Benchmark | gpt-oss-120b | Rank among available | Best available |
|---|---|---|---|
| APEX-AgentsAPEX-Agents: tasks passed · reported | 4.4% | 37th of 37 | Claude Sonnet 5.5 75.5% |
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | gpt-oss-120b | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 11.6 | 129th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 19.6% | 104th of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 78.2% | 100th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | gpt-oss-120b | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,352 | 119th of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 38.5 | 86th of 124 | Gemini 3.8 Flash 78.6 |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | gpt-oss-120b | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 14.2% | 62nd of 71 | GPT-5.4 nano 3.1% |
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,385 | 103rd of 109 | Gemini 4 Argon 1,511 |
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligencegpt-oss-20b$0.06 blended · Intelligence Index 10.0Compare with gpt-oss-120b →
- OpenAI's newer, at least as capable modelGPT-6 Astra$20.00 blended · Intelligence Index 52.7Compare with gpt-oss-120b →
Against gpt-oss-120b at $0.20 blended, Intelligence Index 11.6. "Similar intelligence" means within 4 points or better.
Where to run it
25 hosts on OpenRouter at the standard service tier, with a median of $0.20 blended per million tokens; quantisation where the host states it: FP4, INT4, BF16, FP8, FP16. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Near AI | FP4 | $0.03 | $0.15 | $0.06 |
| Venice | INT4 | $0.03 | $0.15 | $0.06 |
| CoreWeave | FP4 | $0.03 | $0.17 | $0.07 |
| DekaLLM | BF16 | $0.03 | $0.18 | $0.07 |
| AkashML | FP4 | $0.03 | $0.19 | $0.07 |
| DeepInfra | BF16 | $0.04 | $0.17 | $0.07 |
| PrimeIntellect | FP4 | $0.06 | $0.12 | $0.07 |
| Crusoe | BF16 | $0.05 | $0.25 | $0.10 |
Other service tiers, not counted above: Parasail fast $0.15 in, $0.75 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 17 dearer hosts are left out.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| gpt-oss-120b | Claude Haiku 5.5 most intelligent at under $0.25 per million tokens | gpt-oss-20b cheapest with similar intelligence | Claude Opus 5.5 most intelligent available today | MiMo-V2.6-Pro most intelligent with open weights | |
|---|---|---|---|---|---|
| Price per million tokens | $0.20 | $0.20 | $0.06 | $8.00 | $0.54 |
| Tokens a second | 259 | 240 | 277 | 96 | 43 |
| Intelligence Index | 11.6 | 43.4 | 10.0 | 57.6 | 46.3 |
| Spring Prompt overall | – | 40 | – | 82 | – |
| Rank among available models, by use case | |||||
| Product listings | – | 20th | – | 13th | – |
| Decks from an analysis | – | 18th | – | 7th | – |
| User surveys | – | 7th | – | 4th | – |
| Marketing planning | – | 30th | – | 9th | – |
| Agents and tool use | 125th of 159 | 28th | 130th | 3rd | 23rd |
| Professional work | 49th of 51 | – | – | 3rd | – |
| Reasoning and knowledge | 118th of 187 | 25th | 132nd | 1st | 13th |
| Writing | 124th of 169 | – | 155th | 5th | 23rd |
| Sticking to the facts | 129th of 139 | – | – | 3rd | 10th |
| Speed under pressure | – | 21st | – | – | – |
| Side by side → | Side by side → | Side by side → | |||
Shaded figures are better than gpt-oss-120b's. A dash means no result.
Where it has been measured
2nd fastest of the 13 models with similar intelligence. 15th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, professional work, and sticking to the facts.
- APEX-Agents1 result
- Arena (formerly LMArena)7 results
- Artificial Analysis26 results
- UGI Leaderboard3 results
- Vectara Hallucination Leaderboard2 results
- Vending-Bench 21 result
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- Berkeley Function Calling Leaderboard (BFCL) V4Not measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- tau2-benchNot measured
Every result
40 published results from 6 sources, each in the source's own units, with the configuration that produced it.
APEX-Agents · reported by APEX-Agents · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| APEX-Agents: tasks passed% of tasks, higher is better | 4.4% | 39 of 39 | gpt-oss-120b | 1 Oct 2026 |
Not shown: Not your firm's documents or tools; graded by rubric, not by a client.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Text factuality: overallArena rating, higher is better | 1,385 1,378–1,391 |
161 of 182 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,352 1,343–1,360 |
208 of 406 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,278 1,268–1,288 |
264 of 411 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,357 1,341–1,373 |
213 of 363 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,323 1,316–1,330 |
230 of 413 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,352 1,347–1,356 |
212 of 413 | gpt-oss-120b | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,309 1,302–1,317 |
241 of 412 | gpt-oss-120b | 2 Oct 2026 |
Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
Artificial Analysis · reported by Artificial Analysis · 26 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 30.4 | 136 of 187 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 21.2 | 152 of 187 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 11.6 | 298 of 413 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 10.2 | 317 of 413 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 78.2% | 189 of 360 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 67.2% | 261 of 360 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 19.6% | 204 of 419 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 5.9% | 332 of 419 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 69.0% | 70 of 288 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: IFBench% of instructions, higher is better | 58.3% | 110 of 288 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 52.0% | 276 of 407 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 46.0% | 291 of 407 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 259 | 9 of 137 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 258 | 10 of 137 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 34.0% | 185 of 205 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 26.2% | 140 of 188 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 13.9% | 151 of 188 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 0.0% | 152 of 204 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 23.5% | 138 of 282 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better | 5.3% | 232 of 282 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 8.22 | 54 of 137 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 8.27 | 55 of 137 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 12.8% | 112 of 175 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 2.9% | 171 of 175 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 65.8% | 137 of 286 | gpt-oss-120b (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ²-bench telecom% of tasks, higher is better | 45.0% | 173 of 286 | gpt-oss-120b (low reasoning) | 20 Oct 2026 |
Not shown: Not your codebase or tools.
UGI Leaderboard · reported by UGI Leaderboard · 3 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 107.0% | 362 of 379 | gpt-oss-120b (medium reasoning) | 1 Oct 2025 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.29 | 360 of 379 | gpt-oss-120b (medium reasoning) | 1 Oct 2025 |
| UGI: writing scorescore out of 100, higher is better | 38.5 | 235 of 379 | gpt-oss-120b (medium reasoning) | 1 Oct 2025 |
Not shown: Not other format limits such as character counts or bullet counts.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 99.9% | 19 of 108 | gpt-oss-120b | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 14.2% | 90 of 108 | gpt-oss-120b | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vending-Bench 2: money after a yearUS dollars, higher is better | $-21.53 | 61 of 63 | gpt-oss-120b | 1 Oct 2026 |
Not shown: Not a real business; one simulated market with set rules.
Will gpt-oss-120b work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.