GLM-5 vs Qwen3.6 35B-A3B vs Qwen3.5 397B-A17B
Too close to call on our weighted score (Qwen3.6 35B-A3B 68, Qwen3.5 397B-A17B 65, GLM-5 55). The right pick depends on what you value most.
Z.ai (Zhipu)GLM-5
55/100- ECI145.8
- Price$1.00 / $3.20
- Context205K
Alibaba (Qwen)Qwen3.6 35B-A3B
68/100- ECI143.9
- Price$0.248 / $1.49
- Context262K
- Alibaba (Qwen)
Qwen3.5 397B-A17B
65/100- ECI146.7
- Price$0.60 / $3.60
- Context262K
Too close to call
It is close. Our weighted score puts them within 3 points (Qwen3.6 35B-A3B 68/100, Qwen3.5 397B-A17B 65/100, GLM-5 55/100), so choose by what matters most for your work: Qwen3.5 397B-A17B for raw capability and Qwen3.6 35B-A3B on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityQwen3.5 397B-A17BCapabilities Index (ECI): Qwen3.5 397B-A17B 146.7 · GLM-5 145.8 · Qwen3.6 35B-A3B 143.9
- Lowest priceQwen3.6 35B-A3BQwen3.6 35B-A3B $0.557 · Qwen3.5 397B-A17B $1.35 · GLM-5 $1.55 per 1M tokens (3:1 blend)
- Longest contextQwen3.6 35B-A3B and Qwen3.5 397B-A17BQwen3.6 35B-A3B 262,144 · Qwen3.5 397B-A17B 262,144 · GLM-5 204,800 tokens
- Widest inputsQwen3.6 35B-A3B and Qwen3.5 397B-A17BGLM-5: Text · Qwen3.6 35B-A3B: Text, Images, Audio, Video · Qwen3.5 397B-A17B: Text, Images, Audio, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | GLM-5 | Qwen3.6 35B-A3B | Qwen3.5 397B-A17B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 70 | 74 |
| Price | 25% | 41 | 62 | 44 |
| Inputs & features | 15% | 35 | 90 | 90 |
| Context window | 10% | 32 | 37 | 37 |
| Overall | 100% | 55/100 | 68/100 | 65/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GLM-5Z.ai (Zhipu) | Qwen3.6 35B-A3BAlibaba (Qwen) | Qwen3.5 397B-A17BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 145.8 | 143.9 | 146.7 (best) |
| ECI rank | #74 of 148 | #83 of 148 | #67 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 87.8% (best) | 84.9% | 86.4% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 20.4% | 31.2% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 80.0% | 86.7% | 88.9% (best) |
| SWE-bench VerifiedFixing real GitHub issues | 72.1% | — | — |
| Price per million tokens | |||
| Input | $1.00 | $0.248 (best) | $0.60 |
| Output | $3.20 | $1.49 (best) | $3.60 |
| Cached input | $0.20 | — | — |
| Blended (3:1) | $1.55 | $0.557 (best) | $1.35 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official Alibaba API | Official Alibaba API |
| Limits | |||
| Context window | 204,800 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Max output | 131,072 tokens (best) | 65,536 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | Yes | Yes |
| Video | No | Yes | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | glm-5 | qwen3.6-35b-a3b | qwen3.5-397b-a17b |
| API providers | 27 | 34 (best) | 23 |
| Released | Feb 12, 2026 | Apr 17, 2026 | Feb 15, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GLM-5$16.40
- Qwen3.6 35B-A3B$5.45
- Qwen3.5 397B-A17B$13.20
Which should you choose?
Which is better: GLM-5, Qwen3.6 35B-A3B or Qwen3.5 397B-A17B?
It is close. Our weighted score puts them within 3 points (Qwen3.6 35B-A3B 68/100, Qwen3.5 397B-A17B 65/100, GLM-5 55/100), so choose by what matters most for your work: Qwen3.5 397B-A17B for raw capability and Qwen3.6 35B-A3B on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GLM-5, Qwen3.6 35B-A3B or Qwen3.5 397B-A17B?
Qwen3.6 35B-A3B is cheaper at $0.248 input / $1.49 output per million tokens (official Alibaba API price). Qwen3.5 397B-A17B costs $0.60 input / $3.60 output per million tokens (official Alibaba API price); GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.557 per million tokens for Qwen3.6 35B-A3B versus $1.35 for Qwen3.5 397B-A17B (2.4× as much) and $1.55 for GLM-5 (2.8× as much).
Which scores higher on benchmarks?
Qwen3.5 397B-A17B scores higher on the Capabilities Index (ECI): Qwen3.5 397B-A17B 146.7 (#67 of 148), GLM-5 145.8 (#74 of 148) and Qwen3.6 35B-A3B 143.9 (#83 of 148). The confidence ranges of the top two overlap (144.8–148.2 vs 143.9–147.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, Qwen3.5 397B-A17B 86.4%, Qwen3.6 35B-A3B 84.9%; OTIS Mock AIME 2024–2025 — Qwen3.5 397B-A17B 88.9%, Qwen3.6 35B-A3B 86.7%, GLM-5 80.0%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.6 35B-A3B and Qwen3.5 397B-A17B yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 397B-A17B 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?
Qwen3.6 35B-A3B and Qwen3.5 397B-A17B have the largest context windows (262,144 and 262,144 tokens), against 204,800 for GLM-5. Maximum output per response: GLM-5 up to 131,072, Qwen3.6 35B-A3B up to 65,536, Qwen3.5 397B-A17B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GLM-5 accepts text; Qwen3.6 35B-A3B accepts text, images, audio and video; Qwen3.5 397B-A17B accepts text, images, audio and video. Qwen3.6 35B-A3B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Qwen3.6 35B-A3B is the newest, released Apr 17, 2026. Qwen3.5 397B-A17B came out Feb 15, 2026; GLM-5 came out Feb 12, 2026.
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.
