Mistral Large 4 vs GPT-5.1 Codex mini vs Inkling Small
Too close to call on our weighted score (Inkling Small 59, Mistral Large 4 56, GPT-5.1 Codex mini 54). The right pick depends on what you value most.
Mistral AIMistral Large 4
56/100- ECI150.6
- Price$0.70 / $2.10
- Context1.05M
OpenAIGPT-5.1 Codex mini
54/100- ECI—
- Price$0.25 / $2.00
- Context400K
Thinking MachinesInkling Small
59/100- ECI150.5
- Price$0.58 / $1.44
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 3 points (Inkling Small 59/100, Mistral Large 4 56/100, GPT-5.1 Codex mini 54/100), so choose by what matters most for your work: GPT-5.1 Codex mini 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 priceGPT-5.1 Codex miniGPT-5.1 Codex mini $0.688 · Inkling Small $0.795 · Mistral Large 4 $1.05 per 1M tokens (3:1 blend)
- Longest contextMistral Large 4 and Inkling SmallMistral Large 4 1,048,576 · Inkling Small 1,048,576 · GPT-5.1 Codex mini 400,000 tokens
- Widest inputsInkling SmallMistral Large 4: Text, Images · GPT-5.1 Codex mini: Text, Images · Inkling Small: Text, Images, Audio
- Self-hostingInkling SmallPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Mistral Large 4 | GPT-5.1 Codex mini | Inkling Small |
|---|---|---|---|---|
| Price | 50% | 47 | 55 | 52 |
| Inputs & features | 30% | 70 | 60 | 70 |
| Context window | 20% | 61 | 44 | 61 |
| Overall | 100% | 56/100 | 54/100 | 59/100 |
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 | Mistral Large 4Mistral AI | GPT-5.1 Codex miniOpenAI | Inkling SmallThinking Machines |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.6 (best) | — | 150.5 |
| ECI rank | #57 of 165 (best) | — | #58 of 165 |
| GPQA DiamondGraduate-level science questions | 88.1% | — | 88.5% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 58.6% (best) | — | 46.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.3% (best) | — | 90.0% |
| SimpleQA VerifiedShort factual questions | 20.0% (best) | — | 19.1% |
| Price per million tokens | |||
| Input | $0.70 | $0.25 (best) | $0.58 |
| Output | $2.10 | $2.00 | $1.44 (best) |
| Cached input | $0.07 (best) | — | $0.116 |
| Blended (3:1) | $1.05 | $0.688 (best) | $0.795 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 16 providers | Official Thinking Machines API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 400,000 tokens | 1,048,576 tokens (best) |
| Max output | 262,144 tokens | 128,000 tokens | 1,048,576 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yes | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | OpenApache-2.0 |
| API model ID | mistral-large-4 | — | thinkingmachines/Inkling-Small |
| API providers | 15 | 16 (best) | 12 |
| Released | Oct 6, 2026 | Nov 13, 2025 | Jul 30, 2026 |
| Knowledge cutoff | — | Sep 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.
- Mistral Large 4$11.20
- GPT-5.1 Codex mini$6.50
- Inkling Small$8.68
Which should you choose?
Which is better: Mistral Large 4, GPT-5.1 Codex mini or Inkling Small?
It is close. Our weighted score puts them within 3 points (Inkling Small 59/100, Mistral Large 4 56/100, GPT-5.1 Codex mini 54/100), so choose by what matters most for your work: GPT-5.1 Codex mini 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, Mistral Large 4, GPT-5.1 Codex mini or Inkling Small?
GPT-5.1 Codex mini is cheaper at $0.25 input / $2.00 output per million tokens (median across 16 API providers). Inkling Small costs $0.58 input / $1.44 output per million tokens (official Thinking Machines API price); Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.688 per million tokens for GPT-5.1 Codex mini versus $0.795 for Inkling Small (1.2× as much) and $1.05 for Mistral Large 4 (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mistral Large 4 has an ECI of 150.6, GPT-5.1 Codex mini has not been scored yet and Inkling Small has an ECI of 150.5.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Large 4, GPT-5.1 Codex mini and Inkling Small 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?
Mistral Large 4 and Inkling Small have the largest context windows (1,048,576 and 1,048,576 tokens), against 400,000 for GPT-5.1 Codex mini. Maximum output per response: Mistral Large 4 up to 262,144, GPT-5.1 Codex mini up to 128,000, Inkling Small up to 1,048,576 tokens.
Which can read images, PDFs, audio or video?
Mistral Large 4 accepts text and images; GPT-5.1 Codex mini accepts text and images; Inkling Small accepts text, images and audio. Inkling Small handles the widest range of inputs.
Are any of these open source?
Inkling Small publishes its weights (Apache-2.0) and can be self-hosted; Mistral Large 4 and GPT-5.1 Codex mini is proprietary.
Which is newer?
Mistral Large 4 is the newest, released Oct 6, 2026. Inkling Small came out Jul 30, 2026; GPT-5.1 Codex mini came out Nov 13, 2025. Knowledge cutoff: GPT-5.1 Codex mini Sep 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 Nov 2, 2026.
Related comparisons
- Mistral Large 4 vs Qwen3.8 27BAlibaba (Qwen) · ECI 151.8
- Mistral Large 4 vs Kimi K2.7 CodeMoonshot AI · ECI 150.2
- Mistral Large 4 vs DeepSeek V4 Pro 0813DeepSeek · ECI 155.9
- GPT-5.1 Codex mini vs Mistral Large 3Mistral AI
- GPT-5.1 Codex mini vs Qwen3 VL 235B A22B InstructAlibaba (Qwen)
- GPT-5.1 Codex mini vs Nova 2 LiteAmazon
