GPT-4o Mini vs gpt-oss-120b
Benchmark Performance
Available Benchmarks
| Benchmark | GPT-4o Mini | gpt-oss-120b |
|---|---|---|
| Aider Polyglotpolyglot-225-5dc9490bb35f · pass_rate_2 · leader | 3.569% of row best · percent · whole; aider 0.69.2.dev | 41.78100% of row best · percent · diff; aider 0.85.3.dev · 3,806.6 output tokens / case |
| LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader | 1,286.2294% of row best · rating · gpt-4o-mini-2024-07-18; 95% CI [1282.70478675, 1289.73790661]; votes 68698; rank 245 | 1,365.91100% of row best · rating · gpt-oss-120b; 95% CI [1361.54274876, 1370.28718499]; votes 29935; rank 172 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark wins | 2 benchmark winsOverall lead |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Technical Differences
Side-by-Side Facts
| Field | GPT-4o Mini | gpt-oss-120b |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Family | Gpt 4o | Gpt Oss 120b |
| Model | GPT-4o Mini | gpt-oss-120b |
| Version | GPT-4o Mini | gpt-oss-120b |
| Lifecycle | active | active |
| Released | Unknown | Unknown |
| Knowledge cutoff | 2023-10-01 | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 128,000 | 131,072 |
| Total parameters | Unknown | 116,829,156,672 |
| Active parameters | Unknown | 5,100,000,000 |
| License | Unknown | apache-2.0 |
| Open weights | No | Yes |
| API available | Yes | Yes |
| Self-hostable | No | Yes |
| Provider access | OpenAI (Standard), Openrouter (Standard) | Deepinfra (Standard), Fireworks AI (Serverless), Groq (Standard), Openrouter (Standard), Together AI (Serverless) |
| Capabilities | chat, generation, tools | chat, generation, reasoning, tools |
13 comparable fields · 9 material differences · Pair passes the primary-source comparison gate
GPT-4o Mini Capabilities
gpt-oss-120b Capabilities
Internal Comparison Graph
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
GPT-4.1OpenAI | vs | GPT-4o MiniOpenAI | family variantsimage, text |
GPT-4.1 NanoOpenAI | vs | GPT-4o MiniOpenAI | family variantsimage, text |
| vs | GPT-4o MiniOpenAI | cross-developer peersimage, text | |
GPT-4o MiniOpenAI | vs |  GLM-OCRZ.ai | cross-developer peersimage, text |
Claude Haiku 4.5Anthropic | vs | GPT-4o MiniOpenAI | cross-developer peersimage, text |
| vs | GPT-4o MiniOpenAI | cross-developer peersimage, text | |
| vs | GPT-4o MiniOpenAI | cross-developer peersimage, text | |
gpt-oss-120bOpenAI | vs | gpt-oss-20bOpenAI | family variantstext |
 Gemini 2.5 FlashGoogle DeepMind | vs | GPT-4o MiniOpenAI | cross-developer peerstext |
Gemini 3.7 FlashGoogle DeepMind | vs | GPT-4o MiniOpenAI | cross-developer peerstext |
GPT-4o MiniOpenAI | vs | gpt-oss-20bOpenAI | family variantstext |
GPT-5.6 SolOpenAI | vs | gpt-oss-120bOpenAI | family variantstext |
Primary Evidence
Sources and Freshness
Questions
GPT-4o Mini vs gpt-oss-120b FAQs
Is GPT-4o Mini or gpt-oss-120b better for coding?+
gpt-oss-120b leads the current coding subset with 1 benchmark win to 0. This describes only the matched benchmark rows shown above.
Which is cheaper, GPT-4o Mini or gpt-oss-120b?+
GPT-4o Mini is $0.15 and gpt-oss-120b is $0.037 per million tokens, so gpt-oss-120b is cheaper on this metric. GPT-4o Mini is $0.60 and gpt-oss-120b is $0.17 per million tokens, so gpt-oss-120b is cheaper on this metric.
Which has a larger context window, GPT-4o Mini or gpt-oss-120b?+
gpt-oss-120b has the larger sourced context window. GPT-4o Mini supports 128,000 and gpt-oss-120b supports 131,072.
Which performs better in benchmarks, GPT-4o Mini or gpt-oss-120b?+
gpt-oss-120b leads the current overall benchmark count. The result uses 2 protocol-matched benchmarks from 2 publishers; it is not a universal quality score.
Can GPT-4o Mini or gpt-oss-120b be self-hosted?+
gpt-oss-120b is the only model in this pair currently marked as self-hostable. GPT-4o Mini is not marked open weight; gpt-oss-120b is open weight.
Can GPT-4o Mini and gpt-oss-120b understand images?+
GPT-4o Mini is documented with image input; gpt-oss-120b is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, GPT-4o Mini or gpt-oss-120b?+
Neither has a larger sourced maximum output. GPT-4o Mini is 16,384 and gpt-oss-120b is —.
Do GPT-4o Mini and gpt-oss-120b support reasoning and tool use?+
GPT-4o Mini: tool calling and image input. gpt-oss-120b: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, GPT-4o Mini or gpt-oss-120b?+
GPT-4o Mini has 2 sourced provider routes; gpt-oss-120b has 5, so gpt-oss-120b has broader tracked availability.
Which offers better value, GPT-4o Mini or gpt-oss-120b?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.