Phi-4-mini vs Pixtral Large (25.02) vs Qwen3-Coder 480B-A35B Instruct
Phi-4-mini comes out ahead, 58 to 33 and 28 on our weighted score, and it is the cheaper option too.
- Our pick
MicrosoftPhi-4-mini
58/100- ECI—
- Price$0.075 / $0.30
- Context128K
Mistral AIPixtral Large (25.02)
33/100- ECI—
- Price$2.00 / $6.00
- Context128K
Alibaba (Qwen)Qwen3-Coder 480B-A35B Instruct
28/100- ECI—
- Price$1.50 / $7.50
- Context262K
Phi-4-mini is our pick
Phi-4-mini is the better all-round choice, scoring 58/100 against Pixtral Large (25.02) (33) and Qwen3-Coder 480B-A35B Instruct (28). It leads on price. Pixtral Large (25.02) wins on inputs & features. Qwen3-Coder 480B-A35B Instruct 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 pricePhi-4-miniPhi-4-mini $0.131 · Pixtral Large (25.02) $3.00 · Qwen3-Coder 480B-A35B Instruct $3.00 per 1M tokens (3:1 blend)
- Longest contextQwen3-Coder 480B-A35B InstructQwen3-Coder 480B-A35B Instruct 262,144 · Phi-4-mini 128,000 · Pixtral Large (25.02) 128,000 tokens
- Widest inputsPixtral Large (25.02)Phi-4-mini: Text · Pixtral Large (25.02): Text, Images · Qwen3-Coder 480B-A35B Instruct: Text
- Self-hostingPhi-4-mini and Qwen3-Coder 480B-A35B InstructPublishes downloadable weights
| Measure | Weight | Phi-4-mini | Pixtral Large (25.02) | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|---|---|
| Price | 50% | 92 | 27 | 27 |
| Inputs & features | 30% | 25 | 50 | 25 |
| Context window | 20% | 24 | 24 | 37 |
| Overall | 100% | 58/100 | 33/100 | 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 | Phi-4-miniMicrosoft | Pixtral Large (25.02)Mistral AI | Qwen3-Coder 480B-A35B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.075 (best) | $2.00 | $1.50 |
| Output | $0.30 (best) | $6.00 | $7.50 |
| Cached input | — | — | — |
| Blended (3:1) | $0.131 (best) | $3.00 | $3.00 |
| Long-context rate | Same rate | Same rate | Over 32K: $2.70 / $13.50 |
| Price source | Official Azure API | Median of 3 providers | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 262,144 tokens (best) |
| Max output | 4,096 tokens | 8,192 tokens | 65,536 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 | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | phi-4-mini | — | qwen3-coder-480b-a35b-instruct |
| API providers | 1 | 3 | 7 (best) |
| Released | Dec 11, 2024 | Apr 8, 2025 | Apr 2025 |
| Knowledge cutoff | Oct 2023 | — | 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.
- Phi-4-mini$1.35
- Pixtral Large (25.02)$32.00
- Qwen3-Coder 480B-A35B Instruct$30.00
Which should you choose?
Which is better: Phi-4-mini, Pixtral Large (25.02) or Qwen3-Coder 480B-A35B Instruct?
Phi-4-mini is the better all-round choice, scoring 58/100 against Pixtral Large (25.02) (33) and Qwen3-Coder 480B-A35B Instruct (28). It leads on price. Pixtral Large (25.02) wins on inputs & features. Qwen3-Coder 480B-A35B Instruct 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, Phi-4-mini, Pixtral Large (25.02) or Qwen3-Coder 480B-A35B Instruct?
Phi-4-mini is cheaper at $0.075 input / $0.30 output per million tokens (official Azure API price). Pixtral Large (25.02) costs $2.00 input / $6.00 output per million tokens (median across 3 API providers); Qwen3-Coder 480B-A35B Instruct costs $1.50 input / $7.50 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.131 per million tokens for Phi-4-mini versus $3.00 for Pixtral Large (25.02) (23× as much) and $3.00 for Qwen3-Coder 480B-A35B Instruct (23× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Phi-4-mini has not been scored yet, Pixtral Large (25.02) 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 Phi-4-mini, Pixtral Large (25.02) 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?
Qwen3-Coder 480B-A35B Instruct has the largest context window at 262,144 tokens, against 128,000 for Phi-4-mini and 128,000 for Pixtral Large (25.02). Maximum output per response: Phi-4-mini up to 4,096, Pixtral Large (25.02) up to 8,192, Qwen3-Coder 480B-A35B Instruct up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Phi-4-mini accepts text; Pixtral Large (25.02) accepts text and images; Qwen3-Coder 480B-A35B Instruct accepts text. Pixtral Large (25.02) handles the widest range of inputs.
Are any of these open source?
Phi-4-mini and Qwen3-Coder 480B-A35B Instruct publishes its weights and can be self-hosted; Pixtral Large (25.02) is proprietary.
Which is newer?
Pixtral Large (25.02) is the newest, released Apr 8, 2025. Qwen3-Coder 480B-A35B Instruct came out Apr 2025; Phi-4-mini came out Dec 11, 2024. Knowledge cutoff: Phi-4-mini Oct 2023, 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.
