Qwen3.5 9B vs Qwen3.5 122B-A10B vs GPT-5 Nano
Qwen3.5 9B comes out ahead, 79 to 75 and 58 on our weighted score, and it is the cheaper option too.
- Our pick
Alibaba (Qwen)Qwen3.5 9B
79/100- ECI139.5
- Price$0.10 / $0.15
- Context262K
- Alibaba (Qwen)
Qwen3.5 122B-A10B
58/100- ECI—
- Price$0.40 / $3.20
- Context262K
OpenAIGPT-5 Nano
75/100- ECI139.4
- Price$0.05 / $0.40
- Context400K
Qwen3.5 9B is our pick
Qwen3.5 9B is the better all-round choice, scoring 79/100 against GPT-5 Nano (75) and Qwen3.5 122B-A10B (58). It leads on price. Qwen3.5 122B-A10B wins on inputs & features. GPT-5 Nano 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 priceQwen3.5 9BQwen3.5 9B $0.113 · GPT-5 Nano $0.138 · Qwen3.5 122B-A10B $1.10 per 1M tokens (3:1 blend)
- Longest contextGPT-5 NanoGPT-5 Nano 400,000 · Qwen3.5 9B 262,144 · Qwen3.5 122B-A10B 262,144 tokens
- Widest inputsQwen3.5 122B-A10BQwen3.5 9B: Text, Images, Video · Qwen3.5 122B-A10B: Text, Images, Audio, Video · GPT-5 Nano: Text, Images
- Self-hostingQwen3.5 9B and Qwen3.5 122B-A10BPublishes downloadable weights
| Measure | Weight | Qwen3.5 9B | Qwen3.5 122B-A10B | GPT-5 Nano |
|---|---|---|---|---|
| Price | 50% | 95 | 48 | 91 |
| Inputs & features | 30% | 80 | 90 | 70 |
| Context window | 20% | 37 | 37 | 44 |
| Overall | 100% | 79/100 | 58/100 | 75/100 |
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 | Qwen3.5 9BAlibaba (Qwen) | Qwen3.5 122B-A10BAlibaba (Qwen) | GPT-5 NanoOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.5 (best) | — | 139.4 |
| ECI rank | #101 of 148 (best) | — | #102 of 148 |
| GPQA DiamondGraduate-level science questions | 79.0% (best) | — | 69.4% |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 20.0% |
| OTIS Mock AIME 2024–2025Competition mathematics | 61.7% | — | 81.1% (best) |
| SimpleQA VerifiedShort factual questions | — | — | 11.7% |
| Price per million tokens | |||
| Input | $0.10 | $0.40 | $0.05 (best) |
| Output | $0.15 (best) | $3.20 | $0.40 |
| Cached input | — | — | $0.005 |
| Blended (3:1) | $0.113 (best) | $1.10 | $0.138 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 14 providers | Official Alibaba API | Official OpenAI API |
| Limits | |||
| Context window | 262,144 tokens | 262,144 tokens | 400,000 tokens (best) |
| Max output | 65,536 tokens | 65,536 tokens | 128,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | Yes | Yesminimal · low · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | qwen3.5-122b-a10b | gpt-5-nano |
| API providers | 15 | 19 | 21 (best) |
| Released | Feb 23, 2026 | Feb 23, 2026 | Aug 7, 2025 |
| Knowledge cutoff | — | — | May 30, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3.5 9B$1.30
- Qwen3.5 122B-A10B$10.40
- GPT-5 Nano$1.30
Which should you choose?
Which is better: Qwen3.5 9B, Qwen3.5 122B-A10B or GPT-5 Nano?
Qwen3.5 9B is the better all-round choice, scoring 79/100 against GPT-5 Nano (75) and Qwen3.5 122B-A10B (58). It leads on price. Qwen3.5 122B-A10B wins on inputs & features. GPT-5 Nano 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, Qwen3.5 9B, Qwen3.5 122B-A10B or GPT-5 Nano?
Qwen3.5 9B is cheaper at $0.10 input / $0.15 output per million tokens (median across 14 API providers). GPT-5 Nano costs $0.05 input / $0.40 output per million tokens (official OpenAI API price); Qwen3.5 122B-A10B costs $0.40 input / $3.20 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.113 per million tokens for Qwen3.5 9B versus $0.138 for GPT-5 Nano (1.2× as much) and $1.10 for Qwen3.5 122B-A10B (9.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3.5 9B has an ECI of 139.5, Qwen3.5 122B-A10B has not been scored yet and GPT-5 Nano has an ECI of 139.4.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 9B, Qwen3.5 122B-A10B and GPT-5 Nano 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?
GPT-5 Nano has the largest context window at 400,000 tokens, against 262,144 for Qwen3.5 9B and 262,144 for Qwen3.5 122B-A10B. Maximum output per response: Qwen3.5 9B up to 65,536, Qwen3.5 122B-A10B up to 65,536, GPT-5 Nano up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Qwen3.5 9B accepts text, images and video; Qwen3.5 122B-A10B accepts text, images, audio and video; GPT-5 Nano accepts text and images. Qwen3.5 122B-A10B handles the widest range of inputs.
Are any of these open source?
Qwen3.5 9B and Qwen3.5 122B-A10B publishes its weights and can be self-hosted; GPT-5 Nano is proprietary.
Which is newer?
Qwen3.5 9B is the newest, released Feb 23, 2026. Qwen3.5 122B-A10B came out Feb 23, 2026; GPT-5 Nano came out Aug 7, 2025. Knowledge cutoff: GPT-5 Nano May 30, 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.
