Inkling Small vs Mistral Large 3 vs Qwen3.8 27B
Inkling Small comes out ahead, 59 to 53 and 52 on our weighted score, though Mistral Large 3 is 6% cheaper per token.
- Our pick
Thinking MachinesInkling Small
59/100- ECI150.5
- Price$0.58 / $1.44
- Context1.05M
Mistral AIMistral Large 3
52/100- ECI—
- Price$0.50 / $1.50
- Context262K
Alibaba (Qwen)Qwen3.8 27B
53/100- ECI151.8
- Price$0.40 / $2.55
- Context262K
Inkling Small is our pick
Inkling Small is the better all-round choice, scoring 59/100 against Qwen3.8 27B (53) and Mistral Large 3 (52). It leads 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 priceMistral Large 3Mistral Large 3 $0.75 · Inkling Small $0.795 · Qwen3.8 27B $0.938 per 1M tokens (3:1 blend)
- Longest contextInkling SmallInkling Small 1,048,576 · Mistral Large 3 262,144 · Qwen3.8 27B 262,144 tokens
- Widest inputsInkling Small and Qwen3.8 27BInkling Small: Text, Images, Audio · Mistral Large 3: Text, Images · Qwen3.8 27B: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Inkling Small | Mistral Large 3 | Qwen3.8 27B |
|---|---|---|---|---|
| Price | 50% | 52 | 53 | 49 |
| Inputs & features | 30% | 70 | 60 | 70 |
| Context window | 20% | 61 | 37 | 37 |
| Overall | 100% | 59/100 | 52/100 | 53/100 |
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 | Inkling SmallThinking Machines | Mistral Large 3Mistral AI | Qwen3.8 27BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.5 | — | 151.8 (best) |
| ECI rank | #58 of 165 | — | #54 of 165 (best) |
| GPQA DiamondGraduate-level science questions | 88.5% | — | — |
| FrontierMath Tiers 1–3Research-level mathematics | 46.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 90.0% | — | — |
| SimpleQA VerifiedShort factual questions | 19.1% | — | — |
| Price per million tokens | |||
| Input | $0.58 | $0.50 | $0.40 (best) |
| Output | $1.44 (best) | $1.50 | $2.55 |
| Cached input | $0.116 | $0.05 (best) | — |
| Blended (3:1) | $0.795 | $0.75 (best) | $0.938 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Thinking Machines API | Official Mistral API | Median of 49 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 262,144 tokens |
| Max output | 1,048,576 tokens (best) | 262,144 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh · max | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Open |
| API model ID | thinkingmachines/Inkling-Small | mistral-large-2512 | — |
| API providers | 12 | 17 | 53 (best) |
| Released | Jul 30, 2026 | Dec 2, 2025 | Aug 14, 2026 |
| Knowledge cutoff | — | Nov 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Inkling Small$8.68
- Mistral Large 3$8.00
- Qwen3.8 27B$9.10
Which should you choose?
Which is better: Inkling Small, Mistral Large 3 or Qwen3.8 27B?
Inkling Small is the better all-round choice, scoring 59/100 against Qwen3.8 27B (53) and Mistral Large 3 (52). It leads 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, Inkling Small, Mistral Large 3 or Qwen3.8 27B?
Mistral Large 3 is cheaper at $0.50 input / $1.50 output per million tokens (official Mistral API price). Inkling Small costs $0.58 input / $1.44 output per million tokens (official Thinking Machines API price); Qwen3.8 27B costs $0.40 input / $2.55 output per million tokens (median across 49 API providers). At a typical mix of three input tokens to one output token, that is $0.75 per million tokens for Mistral Large 3 versus $0.795 for Inkling Small (1.1× as much) and $0.938 for Qwen3.8 27B (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Inkling Small has an ECI of 150.5, Mistral Large 3 has not been scored yet and Qwen3.8 27B has an ECI of 151.8.
Which is better for coding?
There are no published SWE-bench Verified results for Inkling Small, Mistral Large 3 and Qwen3.8 27B 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?
Inkling Small has the largest context window at 1,048,576 tokens, against 262,144 for Mistral Large 3 and 262,144 for Qwen3.8 27B. Maximum output per response: Inkling Small up to 1,048,576, Mistral Large 3 up to 262,144, Qwen3.8 27B up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Inkling Small accepts text, images and audio; Mistral Large 3 accepts text and images; Qwen3.8 27B accepts text, images and video. Inkling Small handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Qwen3.8 27B is the newest, released Aug 14, 2026. Inkling Small came out Jul 30, 2026; Mistral Large 3 came out Dec 2, 2025. Knowledge cutoff: Mistral Large 3 Nov 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.
