Qwen3 235B-A22B Instruct 2507 vs o4-mini-deep-research vs GPT OSS 120B
No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.
Price in rating: Included · Exclude price
Alibaba (Qwen)
Qwen3 235B-A22B Instruct 2507
53/100- ECI138.1
- Price$0.15 / $0.60
- Context262K
OpenAI
o4-mini-deep-research
38/100- ECI—
- Price$1.80 / $7.20
- Context200K
OpenAI
GPT OSS 120B
54/100- ECI140.2
- Price$0.15 / $0.60
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (GPT OSS 120B 54/100, Qwen3 235B-A22B Instruct 2507 53/100, o4-mini-deep-research 38/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceQwen3 235B-A22B Instruct 2507 and GPT OSS 120BQwen3 235B-A22B Instruct 2507 $0.263 · GPT OSS 120B $0.263 · o4-mini-deep-research $3.15 per 1M tokens (3:1 blend)
- Longest contextQwen3 235B-A22B Instruct 2507Qwen3 235B-A22B Instruct 2507 262,144 · o4-mini-deep-research 200,000 · GPT OSS 120B 131,072 tokens
- Widest inputso4-mini-deep-researchQwen3 235B-A22B Instruct 2507: Text · o4-mini-deep-research: Text, Images · GPT OSS 120B: Text
- Self-hostingQwen3 235B-A22B Instruct 2507 and GPT OSS 120BPublishes downloadable weights (Apache 2.0)
| Measure | Weight | Qwen3 235B-A22B Instruct 2507 | o4-mini-deep-research | GPT OSS 120B |
|---|---|---|---|---|
| Price | 50% | 74 | 25 | 74 |
| Inputs & features | 30% | 25 | 60 | 35 |
| Context window | 20% | 43 | 39 | 32 |
| Specs & price only | 100% | 53/100 | 38/100 | 54/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 138.1 | — | 140.2 (best) |
| ECI rank | #120 of 158 | — | #115 of 158 (best) |
| GPQA DiamondGraduate-level science questions | — | — | 75.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | — | 88.9% |
| Price per million tokens | |||
| Input | $0.15 (best) | $1.80 | $0.15 (best) |
| Output | $0.60 (best) | $7.20 | $0.60 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.263 (best) | $3.15 | $0.263 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 23 providers | Median of 1 providers | Median of 77 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 200,000 tokens | 131,072 tokens |
| Max output | 16,384 tokens | 100,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache 2.0 | Proprietary | Open |
| API model ID | — | — | — |
| API providers | 25 | 1 | 80 (best) |
| Released | Jul 21, 2025 | Jun 26, 2025 | Aug 5, 2025 |
| Knowledge cutoff | — | May 2024 | Jun 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Qwen3 235B-A22B Instruct 2507$2.70
o4-mini-deep-research$32.40
GPT OSS 120B$2.70
Which should you choose?
Which is better: Qwen3 235B-A22B Instruct 2507, o4-mini-deep-research or GPT OSS 120B?
There is not enough shared capability evidence to name an overall winner. The scores (GPT OSS 120B 54/100, Qwen3 235B-A22B Instruct 2507 53/100, o4-mini-deep-research 38/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Qwen3 235B-A22B Instruct 2507, o4-mini-deep-research or GPT OSS 120B?
Qwen3 235B-A22B Instruct 2507 is cheaper at $0.15 input / $0.60 output per million tokens (median across 23 API providers). GPT OSS 120B costs $0.15 input / $0.60 output per million tokens (median across 77 API providers); o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Qwen3 235B-A22B Instruct 2507 versus $0.263 for GPT OSS 120B (1× as much) and $3.15 for o4-mini-deep-research (12× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3 235B-A22B Instruct 2507 has an ECI of 138.1, o4-mini-deep-research has not been scored yet and GPT OSS 120B has an ECI of 140.2.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 235B-A22B Instruct 2507, o4-mini-deep-research and GPT OSS 120B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. 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 200,000 for o4-mini-deep-research and 131,072 for GPT OSS 120B. Maximum output per response: Qwen3 235B-A22B Instruct 2507 up to 16,384, o4-mini-deep-research up to 100,000, GPT OSS 120B up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3 235B-A22B Instruct 2507 accepts text; o4-mini-deep-research accepts text and images; GPT OSS 120B accepts text. o4-mini-deep-research handles the widest range of inputs.
Are any of these open source?
Qwen3 235B-A22B Instruct 2507 and GPT OSS 120B publishes its weights (Apache 2.0) and can be self-hosted; o4-mini-deep-research is proprietary.
Which is newer?
GPT OSS 120B is the newest, released Aug 5, 2025. Qwen3 235B-A22B Instruct 2507 came out Jul 21, 2025; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: o4-mini-deep-research May 2024, GPT OSS 120B Jun 2024.
How do you decide the winner?
This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 Nov 18, 2026.