GPT-5-Codex vs Magistral Medium vs Qwen3-Coder 480B-A35B Instruct
GPT-5-Codex comes out ahead, 42 to 30 and 28 on our weighted score, though Magistral Medium is 20% cheaper per token.
- Our pick
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Mistral AIMagistral Medium
30/100- ECI—
- Price$2.00 / $5.00
- Context128K
Alibaba (Qwen)Qwen3-Coder 480B-A35B Instruct
28/100- ECI—
- Price$1.50 / $7.50
- Context262K
GPT-5-Codex is our pick
GPT-5-Codex is the better all-round choice, scoring 42/100 against Magistral Medium (30) and Qwen3-Coder 480B-A35B Instruct (28). It leads on inputs & features and context window. Magistral Medium wins on 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 priceMagistral MediumMagistral Medium $2.75 · Qwen3-Coder 480B-A35B Instruct $3.00 · GPT-5-Codex $3.44 per 1M tokens (3:1 blend)
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Qwen3-Coder 480B-A35B Instruct 262,144 · Magistral Medium 128,000 tokens
- Widest inputsGPT-5-CodexGPT-5-Codex: Text, Images · Magistral Medium: Text · Qwen3-Coder 480B-A35B Instruct: Text
- Self-hostingQwen3-Coder 480B-A35B InstructPublishes downloadable weights
| Measure | Weight | GPT-5-Codex | Magistral Medium | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|---|---|
| Price | 50% | 24 | 29 | 27 |
| Inputs & features | 30% | 70 | 35 | 25 |
| Context window | 20% | 44 | 24 | 37 |
| Overall | 100% | 42/100 | 30/100 | 28/100 |
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-5-CodexOpenAI | Magistral MediumMistral AI | Qwen3-Coder 480B-A35B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.25 (best) | $2.00 | $1.50 |
| Output | $10.00 | $5.00 (best) | $7.50 |
| Cached input | — | — | — |
| Blended (3:1) | $3.44 | $2.75 (best) | $3.00 |
| Long-context rate | Same rate | Same rate | Over 32K: $2.70 / $13.50 |
| Price source | Median of 3 providers | Official Mistral API | Official Alibaba API |
| Limits | |||
| Context window | 400,000 tokens (best) | 128,000 tokens | 262,144 tokens |
| Max output | 128,000 tokens (best) | 16,384 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | 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 | Proprietary | Proprietary | Open |
| API model ID | — | magistral-medium-latest | qwen3-coder-480b-a35b-instruct |
| API providers | 3 | 4 | 7 (best) |
| Released | Sep 15, 2025 | Mar 17, 2025 | Apr 2025 |
| Knowledge cutoff | Sep 30, 2024 | Jun 2025 | Apr 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-5-Codex$32.50
- Magistral Medium$30.00
- Qwen3-Coder 480B-A35B Instruct$30.00
Which should you choose?
Which is better: GPT-5-Codex, Magistral Medium or Qwen3-Coder 480B-A35B Instruct?
GPT-5-Codex is the better all-round choice, scoring 42/100 against Magistral Medium (30) and Qwen3-Coder 480B-A35B Instruct (28). It leads on inputs & features and context window. Magistral Medium wins on 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, GPT-5-Codex, Magistral Medium or Qwen3-Coder 480B-A35B Instruct?
Magistral Medium is cheaper at $2.00 input / $5.00 output per million tokens (official Mistral API price). Qwen3-Coder 480B-A35B Instruct costs $1.50 input / $7.50 output per million tokens (official Alibaba API price); 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 $2.75 per million tokens for Magistral Medium versus $3.00 for Qwen3-Coder 480B-A35B Instruct (1.1× as much) and $3.44 for GPT-5-Codex (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5-Codex has not been scored yet, Magistral Medium has not been scored yet and Qwen3-Coder 480B-A35B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5-Codex, Magistral Medium and Qwen3-Coder 480B-A35B Instruct 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 262,144 for Qwen3-Coder 480B-A35B Instruct and 128,000 for Magistral Medium. Maximum output per response: GPT-5-Codex up to 128,000, Magistral Medium up to 16,384, Qwen3-Coder 480B-A35B Instruct up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GPT-5-Codex accepts text and images; Magistral Medium accepts text; Qwen3-Coder 480B-A35B Instruct accepts text. GPT-5-Codex handles the widest range of inputs.
Are any of these open source?
Qwen3-Coder 480B-A35B Instruct publishes its weights and can be self-hosted; GPT-5-Codex and Magistral Medium is proprietary.
Which is newer?
GPT-5-Codex is the newest, released Sep 15, 2025. Qwen3-Coder 480B-A35B Instruct came out Apr 2025; Magistral Medium came out Mar 17, 2025. Knowledge cutoff: GPT-5-Codex Sep 30, 2024, Magistral Medium Jun 2025, Qwen3-Coder 480B-A35B Instruct Apr 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.
