GLM-5 vs Qwen3.5 397B-A17B vs Kimi K2 Thinking
Qwen3.5 397B-A17B comes out ahead, 65 to 58 and 55 on our weighted score, though Kimi K2 Thinking is 20% cheaper per token.
Z.ai (Zhipu)GLM-5
55/100- ECI145.8
- Price$1.00 / $3.20
- Context205K
- Our pick
Alibaba (Qwen)Qwen3.5 397B-A17B
65/100- ECI146.7
- Price$0.60 / $3.60
- Context262K
Moonshot AIKimi K2 Thinking
58/100- ECI146.0
- Price$0.60 / $2.50
- Context262K
Qwen3.5 397B-A17B is our pick
Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against Kimi K2 Thinking (58) and GLM-5 (55). It leads on inputs & features. Kimi K2 Thinking wins 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 · Kimi K2 Thinking 146.0 · GLM-5 145.8
- Lowest priceKimi K2 ThinkingKimi K2 Thinking $1.07 · Qwen3.5 397B-A17B $1.35 · GLM-5 $1.55 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 397B-A17B and Kimi K2 ThinkingQwen3.5 397B-A17B 262,144 · Kimi K2 Thinking 262,144 · GLM-5 204,800 tokens
- Widest inputsQwen3.5 397B-A17BGLM-5: Text · Qwen3.5 397B-A17B: Text, Images, Audio, Video · Kimi K2 Thinking: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | GLM-5 | Qwen3.5 397B-A17B | Kimi K2 Thinking |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 74 | 73 |
| Price | 25% | 41 | 44 | 48 |
| Inputs & features | 15% | 35 | 90 | 35 |
| Context window | 10% | 32 | 37 | 37 |
| Overall | 100% | 55/100 | 65/100 | 58/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GLM-5Z.ai (Zhipu) | Qwen3.5 397B-A17BAlibaba (Qwen) | Kimi K2 ThinkingMoonshot AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 145.8 | 146.7 (best) | 146.0 |
| ECI rank | #74 of 148 | #67 of 148 (best) | #72 of 148 |
| GPQA DiamondGraduate-level science questions | 87.8% (best) | 86.4% | 84.2% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 31.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 80.0% | 88.9% (best) | 83.1% |
| SWE-bench VerifiedFixing real GitHub issues | 72.1% | — | — |
| Price per million tokens | |||
| Input | $1.00 | $0.60 (best) | $0.60 (best) |
| Output | $3.20 | $3.60 | $2.50 (best) |
| Cached input | $0.20 | — | — |
| Blended (3:1) | $1.55 | $1.35 | $1.07 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official Alibaba API | Median of 10 providers |
| Limits | |||
| Context window | 204,800 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Max output | 131,072 tokens | 65,536 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | glm-5 | qwen3.5-397b-a17b | — |
| API providers | 27 (best) | 23 | 10 |
| Released | Feb 12, 2026 | Feb 15, 2026 | Nov 6, 2025 |
| Knowledge cutoff | — | — | Aug 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-5$16.40
- Qwen3.5 397B-A17B$13.20
- Kimi K2 Thinking$11.00
Which should you choose?
Which is better: GLM-5, Qwen3.5 397B-A17B or Kimi K2 Thinking?
Qwen3.5 397B-A17B is the better all-round choice, scoring 65/100 against Kimi K2 Thinking (58) and GLM-5 (55). It leads on inputs & features. Kimi K2 Thinking wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GLM-5, Qwen3.5 397B-A17B or Kimi K2 Thinking?
Kimi K2 Thinking is cheaper at $0.60 input / $2.50 output per million tokens (median across 10 API providers). 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 $1.07 per million tokens for Kimi K2 Thinking versus $1.35 for Qwen3.5 397B-A17B (1.3× as much) and $1.55 for GLM-5 (1.4× 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), Kimi K2 Thinking 146.0 (#72 of 148) and GLM-5 145.8 (#74 of 148). The confidence ranges of the top two overlap (144.8–148.2 vs 143.4–147.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, Qwen3.5 397B-A17B 86.4%, Kimi K2 Thinking 84.2%; OTIS Mock AIME 2024–2025 — Qwen3.5 397B-A17B 88.9%, Kimi K2 Thinking 83.1%, GLM-5 80.0%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.5 397B-A17B and Kimi K2 Thinking 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?
Qwen3.5 397B-A17B and Kimi K2 Thinking 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, Qwen3.5 397B-A17B up to 65,536, Kimi K2 Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GLM-5 accepts text; Qwen3.5 397B-A17B accepts text, images, audio and video; Kimi K2 Thinking accepts text. Qwen3.5 397B-A17B 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?
Qwen3.5 397B-A17B is the newest, released Feb 15, 2026. GLM-5 came out Feb 12, 2026; Kimi K2 Thinking came out Nov 6, 2025. Knowledge cutoff: Kimi K2 Thinking Aug 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.
Related comparisons
- GLM-5 vs GPT-5.4 miniOpenAI · ECI 148.8
- GLM-5 vs Nemotron 3 Ultra 550B A55BNVIDIA · ECI 146.2
- Qwen3.5 397B-A17B vs Kimi K2.5Moonshot AI · ECI 148.0
- Qwen3.5 397B-A17B vs GPT-5.4 miniOpenAI · ECI 148.8
- Qwen3.5 397B-A17B vs Nemotron 3 Ultra 550B A55BNVIDIA · ECI 146.2
- Kimi K2 Thinking vs Qwen3.5 PlusAlibaba (Qwen) · ECI 146.8
