Inkling vs Mistral Medium 3.5 vs Qwen3.6 Max Preview
Inkling comes out ahead, 59 to 55 and 54 on our weighted score, though Qwen3.6 Max Preview is 43% cheaper per token.
- Our pick
Thinking MachinesInkling
59/100- ECI148.6
- Price$3.74 / $9.36
- Context1.05M
Mistral AIMistral Medium 3.5
55/100- ECI141.4
- Price$1.50 / $7.50
- Context262K
Alibaba (Qwen)Qwen3.6 Max Preview
54/100- ECI149.2
- Price$1.30 / $7.80
- Context262K
Inkling is our pick
Inkling is the better all-round choice, scoring 59/100 against Mistral Medium 3.5 (55) and Qwen3.6 Max Preview (54). It leads on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3.6 Max PreviewCapabilities Index (ECI): Qwen3.6 Max Preview 149.2 · Inkling 148.6 · Mistral Medium 3.5 141.4
- Lowest priceQwen3.6 Max PreviewQwen3.6 Max Preview $2.92 · Mistral Medium 3.5 $3.00 · Inkling $5.14 per 1M tokens (3:1 blend)
- Longest contextInklingInkling 1,048,576 · Mistral Medium 3.5 262,144 · Qwen3.6 Max Preview 262,144 tokens
- Widest inputsInklingInkling: Text, Images, Audio · Mistral Medium 3.5: Text, Images · Qwen3.6 Max Preview: Text
- Self-hostingInkling and Mistral Medium 3.5Publishes downloadable weights (Apache-2.0)
| Measure | Weight | Inkling | Mistral Medium 3.5 | Qwen3.6 Max Preview |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 76 | 67 | 77 |
| Price | 25% | 16 | 27 | 28 |
| Inputs & features | 15% | 70 | 70 | 35 |
| Context window | 10% | 61 | 37 | 37 |
| Overall | 100% | 59/100 | 55/100 | 54/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | InklingThinking Machines | Mistral Medium 3.5Mistral AI | Qwen3.6 Max PreviewAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 148.6 | 141.4 | 149.2 (best) |
| ECI rank | #57 of 148 | #95 of 148 | #54 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 88.3% (best) | — | 87.4% |
| FrontierMath Tiers 1–3Research-level mathematics | 33.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.9% | — | 91.1% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 76.7% |
| SimpleQA VerifiedShort factual questions | 40.3% | — | 52.0% (best) |
| Price per million tokens | |||
| Input | $3.74 | $1.50 | $1.30 (best) |
| Output | $9.36 | $7.50 (best) | $7.80 |
| Cached input | $0.748 | $0.15 | $0.13 (best) |
| Blended (3:1) | $5.14 | $3.00 | $2.92 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Thinking Machines API | Official Mistral API | Official Alibaba API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 262,144 tokens |
| Max output | 1,048,576 tokens (best) | 262,144 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | Yes | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high · xhigh · max | Yeshigh | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Proprietary |
| API model ID | thinkingmachines/Inkling:peft:262144 | mistral-medium-2604 | qwen3.6-max-preview |
| API providers | 23 (best) | 12 | 10 |
| Released | Jul 15, 2026 | Apr 29, 2026 | Apr 20, 2026 |
| Knowledge cutoff | — | — | 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.
- Inkling$56.12
- Mistral Medium 3.5$30.00
- Qwen3.6 Max Preview$28.60
Which should you choose?
Which is better: Inkling, Mistral Medium 3.5 or Qwen3.6 Max Preview?
Inkling is the better all-round choice, scoring 59/100 against Mistral Medium 3.5 (55) and Qwen3.6 Max Preview (54). It leads on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Inkling, Mistral Medium 3.5 or Qwen3.6 Max Preview?
Qwen3.6 Max Preview is cheaper at $1.30 input / $7.80 output per million tokens (official Alibaba API price). Mistral Medium 3.5 costs $1.50 input / $7.50 output per million tokens (official Mistral API price); Inkling costs $3.74 input / $9.36 output per million tokens (official Thinking Machines API price). At a typical mix of three input tokens to one output token, that is $2.92 per million tokens for Qwen3.6 Max Preview versus $3.00 for Mistral Medium 3.5 (1× as much) and $5.14 for Inkling (1.8× as much).
Which scores higher on benchmarks?
Qwen3.6 Max Preview scores higher on the Capabilities Index (ECI): Qwen3.6 Max Preview 149.2 (#54 of 148), Inkling 148.6 (#57 of 148) and Mistral Medium 3.5 141.4 (#95 of 148). The confidence ranges of the top two overlap (147.6–152.0 vs 145.7–150.6), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Inkling and Mistral Medium 3.5 yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 Max Preview leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Inkling has the largest context window at 1,048,576 tokens, against 262,144 for Mistral Medium 3.5 and 262,144 for Qwen3.6 Max Preview. Maximum output per response: Inkling up to 1,048,576, Mistral Medium 3.5 up to 262,144, Qwen3.6 Max Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Inkling accepts text, images and audio; Mistral Medium 3.5 accepts text and images; Qwen3.6 Max Preview accepts text. Inkling handles the widest range of inputs.
Are any of these open source?
Inkling and Mistral Medium 3.5 publishes its weights (Apache-2.0) and can be self-hosted; Qwen3.6 Max Preview is proprietary.
Which is newer?
Inkling is the newest, released Jul 15, 2026. Mistral Medium 3.5 came out Apr 29, 2026; Qwen3.6 Max Preview came out Apr 20, 2026. Knowledge cutoff: Qwen3.6 Max Preview 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.
