GLM-4.7-Flash vs Mistral Small 3.2 vs Qwen Turbo
Mistral Small 3.2 comes out ahead, 52 to 48 and 48 on our weighted score, though Qwen Turbo is 42% cheaper per token.
Z.ai (Zhipu)
GLM-4.7-Flash
48/100- ECI—
- Price$0.06 / $0.40
- Context200K
- Our pick
Mistral AI
Mistral Small 3.2
52/100- ECI131.7
- Price$0.10 / $0.30
- Context128K
Alibaba (Qwen)
Qwen Turbo
48/100- ECI—
- Price$0.05 / $0.20
- Context1M
Mistral Small 3.2 is our pick
Mistral Small 3.2 is the better all-round choice, scoring 52/100 against GLM-4.7-Flash (48) and Qwen Turbo (48). It leads on capability and inputs & features. Qwen Turbo wins on price and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because GLM-4.7-Flash and Qwen Turbo has no Capabilities Index score yet.
- CapabilityMistral Small 3.2Shared benchmarks: Mistral Small 3.2 39.7% · GLM-4.7-Flash 35.1% · Qwen Turbo 24.0%
- Lowest priceQwen TurboQwen Turbo $0.087 · GLM-4.7-Flash $0.145 · Mistral Small 3.2 $0.15 per 1M tokens (3:1 blend)
- Longest contextQwen TurboQwen Turbo 1,000,000 · GLM-4.7-Flash 200,000 · Mistral Small 3.2 128,000 tokens
- Widest inputsMistral Small 3.2GLM-4.7-Flash: Text · Mistral Small 3.2: Text, Images · Qwen Turbo: Text
- Self-hostingGLM-4.7-Flash and Mistral Small 3.2Publishes downloadable weights
| Measure | Weight | GLM-4.7-Flash | Mistral Small 3.2 | Qwen Turbo |
|---|---|---|---|---|
| CapabilityShared benchmarks | 50% | 35 | 40 | 24 |
| Price | 25% | 90 | 89 | 100 |
| Inputs & features | 15% | 35 | 50 | 35 |
| Context window | 10% | 32 | 24 | 60 |
| Overall | 100% | 48/100 | 52/100 | 48/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 131.7 | — |
| ECI rank | — | #123 of 148 | — |
| GPQA DiamondGraduate-level science questions | 45.1% | 49.1% (best) | 41.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 25.0% | 30.3% (best) | 6.1% |
| Price per million tokens | |||
| Input | $0.06 | $0.10 | $0.05 (best) |
| Output | $0.40 | $0.30 | $0.20 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.145 | $0.15 | $0.087 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 13 providers | Official Mistral API | Official Alibaba API |
| Limits | |||
| Context window | 200,000 tokens | 128,000 tokens | 1,000,000 tokens (best) |
| Max output | 131,072 tokens (best) | 16,384 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | glm-4.7-flash | mistral-small-2506 | qwen-turbo |
| API providers | 19 (best) | 6 | 3 |
| Released | Jan 19, 2026 | Jun 20, 2025 | Nov 1, 2024 |
| Knowledge cutoff | Apr 2025 | Mar 2025 | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
GLM-4.7-Flash$1.41
Mistral Small 3.2$1.60
Qwen Turbo$0.90
Which should you choose?
Which is better: GLM-4.7-Flash, Mistral Small 3.2 or Qwen Turbo?
Mistral Small 3.2 is the better all-round choice, scoring 52/100 against GLM-4.7-Flash (48) and Qwen Turbo (48). It leads on capability and inputs & features. Qwen Turbo wins on price and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because GLM-4.7-Flash and Qwen Turbo has no Capabilities Index score yet.
Which is cheaper, GLM-4.7-Flash, Mistral Small 3.2 or Qwen Turbo?
Qwen Turbo is cheaper at $0.05 input / $0.20 output per million tokens (official Alibaba API price). GLM-4.7-Flash costs $0.06 input / $0.40 output per million tokens (median across 13 API providers; free on Z.AI); Mistral Small 3.2 costs $0.10 input / $0.30 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.087 per million tokens for Qwen Turbo versus $0.145 for GLM-4.7-Flash (1.7× as much) and $0.15 for Mistral Small 3.2 (1.7× as much).
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Mistral Small 3.2 39.7%, GLM-4.7-Flash 35.1% and Qwen Turbo 24.0%. On individual benchmarks: GPQA Diamond — Mistral Small 3.2 49.1%, GLM-4.7-Flash 45.1%, Qwen Turbo 41.8%; OTIS Mock AIME 2024–2025 — Mistral Small 3.2 30.3%, GLM-4.7-Flash 25.0%, Qwen Turbo 6.1%.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.7-Flash, Mistral Small 3.2 and Qwen Turbo yet, so there is no like-for-like coding score. On overall capability, Mistral Small 3.2 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?
Qwen Turbo has the largest context window at 1,000,000 tokens, against 200,000 for GLM-4.7-Flash and 128,000 for Mistral Small 3.2. Maximum output per response: GLM-4.7-Flash up to 131,072, Mistral Small 3.2 up to 16,384, Qwen Turbo up to 16,384 tokens.
Which can read images, PDFs, audio or video?
GLM-4.7-Flash accepts text; Mistral Small 3.2 accepts text and images; Qwen Turbo accepts text. Mistral Small 3.2 handles the widest range of inputs.
Are any of these open source?
GLM-4.7-Flash and Mistral Small 3.2 publishes its weights and can be self-hosted; Qwen Turbo is proprietary.
Which is newer?
GLM-4.7-Flash is the newest, released Jan 19, 2026. Mistral Small 3.2 came out Jun 20, 2025; Qwen Turbo came out Nov 1, 2024. Knowledge cutoff: GLM-4.7-Flash Apr 2025, Mistral Small 3.2 Mar 2025, Qwen Turbo Apr 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 Oct 4, 2026.