Qwen3 VL 235B A22B Thinking vs GPT-5-Codex vs Apertus 70B
Qwen3 VL 235B A22B Thinking comes out ahead, 48 to 42 and 33 on our weighted score, though Apertus 70B is 6% cheaper per token.
- Our pick
Alibaba (Qwen)Qwen3 VL 235B A22B Thinking
48/100- ECI—
- Price$0.40 / $4.00
- Context131K
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Swiss AI
Apertus 70B
33/100- ECI—
- Price$0.82 / $2.42
- Context66K
Qwen3 VL 235B A22B Thinking is our pick
Qwen3 VL 235B A22B Thinking is the better all-round choice, scoring 48/100 against GPT-5-Codex (42) and Apertus 70B (33). GPT-5-Codex 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 priceApertus 70BApertus 70B $1.22 · Qwen3 VL 235B A22B Thinking $1.30 · GPT-5-Codex $3.44 per 1M tokens (3:1 blend)
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Qwen3 VL 235B A22B Thinking 131,072 · Apertus 70B 65,536 tokens
- Widest inputsQwen3 VL 235B A22B Thinking and GPT-5-CodexQwen3 VL 235B A22B Thinking: Text, Images · GPT-5-Codex: Text, Images · Apertus 70B: Text
- Self-hostingQwen3 VL 235B A22B Thinking and Apertus 70BPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Qwen3 VL 235B A22B Thinking | GPT-5-Codex | Apertus 70B |
|---|---|---|---|---|
| Price | 50% | 44 | 24 | 46 |
| Inputs & features | 30% | 70 | 70 | 25 |
| Context window | 20% | 24 | 44 | 12 |
| Overall | 100% | 48/100 | 42/100 | 33/100 |
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 VL 235B A22B ThinkingAlibaba (Qwen) | GPT-5-CodexOpenAI | Apertus 70BSwiss AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $1.25 | $0.82 |
| Output | $4.00 | $10.00 | $2.42 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $1.30 | $3.44 | $1.22 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 9 providers | Median of 3 providers | Median of 3 providers |
| Limits | |||
| Context window | 131,072 tokens | 400,000 tokens (best) | 65,536 tokens |
| Max output | 32,768 tokens | 128,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | 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 | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | OpenApache-2.0 |
| API model ID | — | — | — |
| API providers | 9 (best) | 3 | 3 |
| Released | Sep 23, 2025 | Sep 15, 2025 | Sep 2, 2025 |
| Knowledge cutoff | Mar 31, 2025 | Sep 30, 2024 | Sep 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3 VL 235B A22B Thinking$12.00
- GPT-5-Codex$32.50
- Apertus 70B$13.04
Which should you choose?
Which is better: Qwen3 VL 235B A22B Thinking, GPT-5-Codex or Apertus 70B?
Qwen3 VL 235B A22B Thinking is the better all-round choice, scoring 48/100 against GPT-5-Codex (42) and Apertus 70B (33). GPT-5-Codex 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 VL 235B A22B Thinking, GPT-5-Codex or Apertus 70B?
Apertus 70B is cheaper at $0.82 input / $2.42 output per million tokens (median across 3 API providers). Qwen3 VL 235B A22B Thinking costs $0.40 input / $4.00 output per million tokens (median across 9 API providers); GPT-5-Codex costs $1.25 input / $10.00 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $1.22 per million tokens for Apertus 70B versus $1.30 for Qwen3 VL 235B A22B Thinking (1.1× as much) and $3.44 for GPT-5-Codex (2.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3 VL 235B A22B Thinking has not been scored yet, GPT-5-Codex has not been scored yet and Apertus 70B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Thinking, GPT-5-Codex and Apertus 70B 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-Codex has the largest context window at 400,000 tokens, against 131,072 for Qwen3 VL 235B A22B Thinking and 65,536 for Apertus 70B. Maximum output per response: Qwen3 VL 235B A22B Thinking up to 32,768, GPT-5-Codex up to 128,000, Apertus 70B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Qwen3 VL 235B A22B Thinking accepts text and images; GPT-5-Codex accepts text and images; Apertus 70B accepts text. Qwen3 VL 235B A22B Thinking handles the widest range of inputs.
Are any of these open source?
Qwen3 VL 235B A22B Thinking and Apertus 70B publishes its weights (Apache-2.0) and can be self-hosted; GPT-5-Codex is proprietary.
Which is newer?
Qwen3 VL 235B A22B Thinking is the newest, released Sep 23, 2025. GPT-5-Codex came out Sep 15, 2025; Apertus 70B came out Sep 2, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Thinking Mar 31, 2025, GPT-5-Codex Sep 30, 2024, Apertus 70B Sep 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.
