GLM-4.7 vs Claude Haiku 4.5 vs Kimi K2.6
Kimi K2.6 comes out ahead, 74 to 68 and 60 on our weighted score, though GLM-4.7 is 42% cheaper per token.
Price in rating: Excluded · Include price
Z.ai (Zhipu)
GLM-4.7
60/100- ECI143.4
- Price$0.60 / $2.20
- Context205K
Anthropic
Claude Haiku 4.5
68/100- ECI142.8
- Price$1.00 / $5.00
- Context200K
- Our pick
Moonshot AI
Kimi K2.6
74/100- ECI151.6
- Price$0.95 / $4.00
- Context262K
Kimi K2.6 is our pick
Kimi K2.6 is the better all-round choice, scoring 74/100 against Claude Haiku 4.5 (68) and GLM-4.7 (60). It leads on capability and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityKimi K2.6Capabilities Index (ECI): Kimi K2.6 151.6 · GLM-4.7 143.4 · Claude Haiku 4.5 142.8
- Lowest priceGLM-4.7GLM-4.7 $1.00 · Kimi K2.6 $1.71 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
- Longest contextKimi K2.6Kimi K2.6 262,144 · GLM-4.7 204,800 · Claude Haiku 4.5 200,000 tokens
- Widest inputsClaude Haiku 4.5 and Kimi K2.6GLM-4.7: Text · Claude Haiku 4.5: Text, Images, PDFs · Kimi K2.6: Text, Images, Video
- Self-hostingGLM-4.7 and Kimi K2.6Publishes downloadable weights
| Measure | Weight | GLM-4.7 | Claude Haiku 4.5 | Kimi K2.6 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 71 | 70 | 79 |
| Inputs & features | 20% | 35 | 80 | 80 |
| Context window | 13% | 39 | 39 | 43 |
| Overall | 100% | 60/100 | 68/100 | 74/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 143.4 | 142.8 | 151.6 (best) |
| ECI rank | #99 of 158 | #102 of 158 | #61 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 83.3% | 71.2% | 90.8% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 57.2% |
| OTIS Mock AIME 2024–2025Competition mathematics | 83.3% | 66.7% | 96.1% (best) |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 76.7% |
| SimpleQA VerifiedShort factual questions | 32.2% | 13.2% | 34.9% (best) |
| Price per million tokens | |||
| Input | $0.60 (best) | $1.00 | $0.95 |
| Output | $2.20 (best) | $5.00 | $4.00 |
| Cached input | $0.11 | $0.10 (best) | $0.16 |
| Blended (3:1) | $1.00 (best) | $2.00 | $1.71 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official Anthropic API | Official Moonshot AI API |
| Limits | |||
| Context window | 204,800 tokens | 200,000 tokens | 262,144 tokens (best) |
| Max output | 131,072 tokens | 64,000 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | glm-4.7 | claude-haiku-4-5 | kimi-k2.6 |
| API providers | 30 | 57 | 64 (best) |
| Released | Dec 22, 2025 | Oct 15, 2025 | Apr 20, 2026 |
| Knowledge cutoff | Apr 2025 | Feb 28, 2025 | Jan 2025 |
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$10.40
Claude Haiku 4.5$20.00
Kimi K2.6$17.50
Which should you choose?
Which is better: GLM-4.7, Claude Haiku 4.5 or Kimi K2.6?
Kimi K2.6 is the better all-round choice, scoring 74/100 against Claude Haiku 4.5 (68) and GLM-4.7 (60). It leads on capability and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, GLM-4.7, Claude Haiku 4.5 or Kimi K2.6?
GLM-4.7 is cheaper at $0.60 input / $2.20 output per million tokens (official Z.AI API price). Kimi K2.6 costs $0.95 input / $4.00 output per million tokens (official Moonshot AI API price); Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for GLM-4.7 versus $1.71 for Kimi K2.6 (1.7× as much) and $2.00 for Claude Haiku 4.5 (2× as much).
Which scores higher on benchmarks?
Kimi K2.6 scores higher on the Capabilities Index (ECI): Kimi K2.6 151.6 (#61 of 158), GLM-4.7 143.4 (#99 of 158) and Claude Haiku 4.5 142.8 (#102 of 158). Their confidence ranges do not overlap (149.9–153.4 vs 141.4–145.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — Kimi K2.6 90.8%, GLM-4.7 83.3%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Kimi K2.6 96.1%, GLM-4.7 83.3%, Claude Haiku 4.5 66.7%; SimpleQA Verified — Kimi K2.6 34.9%, GLM-4.7 32.2%, Claude Haiku 4.5 13.2%.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.7 and Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, Kimi K2.6 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?
Kimi K2.6 has the largest context window at 262,144 tokens, against 204,800 for GLM-4.7 and 200,000 for Claude Haiku 4.5. Maximum output per response: GLM-4.7 up to 131,072, Claude Haiku 4.5 up to 64,000, Kimi K2.6 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GLM-4.7 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; Kimi K2.6 accepts text, images and video. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
GLM-4.7 and Kimi K2.6 publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.
Which is newer?
Kimi K2.6 is the newest, released Apr 20, 2026. GLM-4.7 came out Dec 22, 2025; Claude Haiku 4.5 came out Oct 15, 2025. Knowledge cutoff: GLM-4.7 Apr 2025, Claude Haiku 4.5 Feb 28, 2025, Kimi K2.6 Jan 2025.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 18, 2026.