GPT OSS 120B vs Mistral Small 3.2 vs Qwen3 235B-A22B Instruct 2507
Too close to call on our weighted score (GPT OSS 120B 61, Mistral Small 3.2 60, Qwen3 235B-A22B Instruct 2507 58). The right pick depends on what you value most.
OpenAIGPT OSS 120B
61/100- ECI140.0
- Price$0.15 / $0.60
- Context131K
Mistral AIMistral Small 3.2
60/100- ECI131.7
- Price$0.10 / $0.30
- Context128K
Alibaba (Qwen)Qwen3 235B-A22B Instruct 2507
58/100- ECI138.9
- Price$0.15 / $0.75
- Context262K
Too close to call
It is close. Our weighted score puts them within 2 points (GPT OSS 120B 61/100, Mistral Small 3.2 60/100, Qwen3 235B-A22B Instruct 2507 58/100), so choose by what matters most for your work: GPT OSS 120B for raw capability, Mistral Small 3.2 on price and Qwen3 235B-A22B Instruct 2507 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT OSS 120BCapabilities Index (ECI): GPT OSS 120B 140.0 · Qwen3 235B-A22B Instruct 2507 138.9 · Mistral Small 3.2 131.7
- Lowest priceMistral Small 3.2Mistral Small 3.2 $0.15 · GPT OSS 120B $0.263 · Qwen3 235B-A22B Instruct 2507 $0.30 per 1M tokens (3:1 blend)
- Longest contextQwen3 235B-A22B Instruct 2507Qwen3 235B-A22B Instruct 2507 262,144 · GPT OSS 120B 131,072 · Mistral Small 3.2 128,000 tokens
- Widest inputsMistral Small 3.2GPT OSS 120B: Text · Mistral Small 3.2: Text, Images · Qwen3 235B-A22B Instruct 2507: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | GPT OSS 120B | Mistral Small 3.2 | Qwen3 235B-A22B Instruct 2507 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 65 | 55 | 64 |
| Price | 25% | 77 | 89 | 75 |
| Inputs & features | 15% | 45 | 50 | 25 |
| Context window | 10% | 24 | 24 | 37 |
| Overall | 100% | 61/100 | 60/100 | 58/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT OSS 120BOpenAI | Mistral Small 3.2Mistral AI | Qwen3 235B-A22B Instruct 2507Alibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.0 (best) | 131.7 | 138.9 |
| ECI rank | #99 of 148 (best) | #123 of 148 | #105 of 148 |
| GPQA DiamondGraduate-level science questions | 75.8% (best) | 49.1% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% (best) | 30.3% | — |
| Price per million tokens | |||
| Input | $0.15 | $0.10 (best) | $0.15 |
| Output | $0.60 | $0.30 (best) | $0.75 |
| Cached input | — | — | — |
| Blended (3:1) | $0.263 | $0.15 (best) | $0.30 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 36 providers | Official Mistral API | Median of 11 providers |
| Limits | |||
| Context window | 131,072 tokens | 128,000 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens (best) | 16,384 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache 2.0 |
| API model ID | — | mistral-small-2506 | — |
| API providers | 39 (best) | 6 | 11 |
| Released | Aug 5, 2025 | Jun 20, 2025 | Jul 21, 2025 |
| Knowledge cutoff | — | Mar 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT OSS 120B$2.70
- Mistral Small 3.2$1.60
- Qwen3 235B-A22B Instruct 2507$3.00
Which should you choose?
Which is better: GPT OSS 120B, Mistral Small 3.2 or Qwen3 235B-A22B Instruct 2507?
It is close. Our weighted score puts them within 2 points (GPT OSS 120B 61/100, Mistral Small 3.2 60/100, Qwen3 235B-A22B Instruct 2507 58/100), so choose by what matters most for your work: GPT OSS 120B for raw capability, Mistral Small 3.2 on price and Qwen3 235B-A22B Instruct 2507 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT OSS 120B, Mistral Small 3.2 or Qwen3 235B-A22B Instruct 2507?
Mistral Small 3.2 is cheaper at $0.10 input / $0.30 output per million tokens (official Mistral API price). GPT OSS 120B costs $0.15 input / $0.60 output per million tokens (median across 36 API providers); Qwen3 235B-A22B Instruct 2507 costs $0.15 input / $0.75 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Mistral Small 3.2 versus $0.263 for GPT OSS 120B (1.8× as much) and $0.30 for Qwen3 235B-A22B Instruct 2507 (2× as much).
Which scores higher on benchmarks?
GPT OSS 120B scores higher on the Capabilities Index (ECI): GPT OSS 120B 140.0 (#99 of 148), Qwen3 235B-A22B Instruct 2507 138.9 (#105 of 148) and Mistral Small 3.2 131.7 (#123 of 148). The confidence ranges of the top two overlap (135.3–142.3 vs 135.8–140.6), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for GPT OSS 120B, Mistral Small 3.2 and Qwen3 235B-A22B Instruct 2507 yet, so there is no like-for-like coding score. On overall capability, GPT OSS 120B leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen3 235B-A22B Instruct 2507 has the largest context window at 262,144 tokens, against 131,072 for GPT OSS 120B and 128,000 for Mistral Small 3.2. Maximum output per response: GPT OSS 120B up to 32,768, Mistral Small 3.2 up to 16,384, Qwen3 235B-A22B Instruct 2507 up to 16,384 tokens.
Which can read images, PDFs, audio or video?
GPT OSS 120B accepts text; Mistral Small 3.2 accepts text and images; Qwen3 235B-A22B Instruct 2507 accepts text. Mistral Small 3.2 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
GPT OSS 120B is the newest, released Aug 5, 2025. Qwen3 235B-A22B Instruct 2507 came out Jul 21, 2025; Mistral Small 3.2 came out Jun 20, 2025. Knowledge cutoff: Mistral Small 3.2 Mar 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
Related comparisons
- GPT OSS 120B vs DeepSeek-V3.1DeepSeek · ECI 139.9
- GPT OSS 120B vs Gemini 2.5 FlashGoogle · ECI 140.8
- Mistral Small 3.2 vs Gemini 2.5 Flash-LiteGoogle · ECI 133.9
- Mistral Small 3.2 vs Qwen3 30B A3BAlibaba (Qwen) · ECI 136.2
- Mistral Small 3.2 vs Llama 4 Maverick 17B InstructMeta · ECI 132.2
- Mistral Small 3.2 vs GPT OSS 20BOpenAI · ECI 137.8
