GPT OSS 120B vs QVQ Max vs Qwen3 235B-A22B Instruct 2507
GPT OSS 120B comes out ahead, 57 to 52 and 40 on our weighted score, and it is the cheaper option too.
- Our pick
OpenAIGPT OSS 120B
57/100- ECI140.0
- Price$0.15 / $0.60
- Context131K
Alibaba (Qwen)QVQ Max
40/100- ECI—
- Price$1.20 / $4.80
- Context131K
- Alibaba (Qwen)
Qwen3 235B-A22B Instruct 2507
52/100- ECI138.9
- Price$0.15 / $0.75
- Context262K
GPT OSS 120B is our pick
GPT OSS 120B is the better all-round choice, scoring 57/100 against Qwen3 235B-A22B Instruct 2507 (52) and QVQ Max (40). It leads on price. QVQ Max wins on inputs & features. Qwen3 235B-A22B Instruct 2507 wins on context window. 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 priceGPT OSS 120BGPT OSS 120B $0.263 · Qwen3 235B-A22B Instruct 2507 $0.30 · QVQ Max $2.10 per 1M tokens (3:1 blend)
- Longest contextQwen3 235B-A22B Instruct 2507Qwen3 235B-A22B Instruct 2507 262,144 · GPT OSS 120B 131,072 · QVQ Max 131,072 tokens
- Widest inputsQVQ MaxGPT OSS 120B: Text · QVQ Max: Text, Images · Qwen3 235B-A22B Instruct 2507: Text
- Self-hostingGPT OSS 120B and Qwen3 235B-A22B Instruct 2507Publishes downloadable weights (Apache 2.0)
| Measure | Weight | GPT OSS 120B | QVQ Max | Qwen3 235B-A22B Instruct 2507 |
|---|---|---|---|---|
| Price | 50% | 77 | 35 | 75 |
| Inputs & features | 30% | 45 | 60 | 25 |
| Context window | 20% | 24 | 24 | 37 |
| Overall | 100% | 57/100 | 40/100 | 52/100 |
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 | GPT OSS 120BOpenAI | QVQ MaxAlibaba (Qwen) | Qwen3 235B-A22B Instruct 2507Alibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 140.0 (best) | — | 138.9 |
| ECI rank | #99 of 148 (best) | — | #105 of 148 |
| GPQA DiamondGraduate-level science questions | 75.8% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% | — | — |
| Price per million tokens | |||
| Input | $0.15 (best) | $1.20 | $0.15 (best) |
| Output | $0.60 (best) | $4.80 | $0.75 |
| Cached input | — | — | — |
| Blended (3:1) | $0.263 (best) | $2.10 | $0.30 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 36 providers | Official Alibaba API | Median of 11 providers |
| Limits | |||
| Context window | 131,072 tokens | 131,072 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens (best) | 8,192 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 | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Proprietary | OpenApache 2.0 |
| API model ID | — | qvq-max | — |
| API providers | 39 (best) | 1 | 11 |
| Released | Aug 5, 2025 | Mar 25, 2025 | Jul 21, 2025 |
| Knowledge cutoff | — | Apr 2024 | — |
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
- QVQ Max$21.60
- Qwen3 235B-A22B Instruct 2507$3.00
Which should you choose?
Which is better: GPT OSS 120B, QVQ Max or Qwen3 235B-A22B Instruct 2507?
GPT OSS 120B is the better all-round choice, scoring 57/100 against Qwen3 235B-A22B Instruct 2507 (52) and QVQ Max (40). It leads on price. QVQ Max wins on inputs & features. Qwen3 235B-A22B Instruct 2507 wins on context window. 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, GPT OSS 120B, QVQ Max or Qwen3 235B-A22B Instruct 2507?
GPT OSS 120B is cheaper at $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); QVQ Max costs $1.20 input / $4.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for GPT OSS 120B versus $0.30 for Qwen3 235B-A22B Instruct 2507 (1.1× as much) and $2.10 for QVQ Max (8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT OSS 120B has an ECI of 140.0, QVQ Max has not been scored yet and Qwen3 235B-A22B Instruct 2507 has an ECI of 138.9.
Which is better for coding?
There are no published SWE-bench Verified results for GPT OSS 120B, QVQ Max and Qwen3 235B-A22B Instruct 2507 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 131,072 for GPT OSS 120B and 131,072 for QVQ Max. Maximum output per response: GPT OSS 120B up to 32,768, QVQ Max up to 8,192, Qwen3 235B-A22B Instruct 2507 up to 16,384 tokens.
Which can read images, PDFs, audio or video?
GPT OSS 120B accepts text; QVQ Max accepts text and images; Qwen3 235B-A22B Instruct 2507 accepts text. QVQ Max handles the widest range of inputs.
Are any of these open source?
GPT OSS 120B and Qwen3 235B-A22B Instruct 2507 publishes its weights (Apache 2.0) and can be self-hosted; QVQ Max 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; QVQ Max came out Mar 25, 2025. Knowledge cutoff: QVQ Max Apr 2024.
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.
