Kimi K2 Thinking vs Grok 4.3 vs GLM-4.7
Grok 4.3 comes out ahead, 67 to 58 and 57 on our weighted score, though GLM-4.7 is 36% cheaper per token.
Price in rating: Included · Exclude price
Moonshot AI
Kimi K2 Thinking
58/100- ECI145.5
- Price$0.60 / $2.50
- Context262K
- Our pick
xAI
Grok 4.3
67/100- ECI149.9
- Price$1.25 / $2.50
- Context1M
Z.ai (Zhipu)
GLM-4.7
57/100- ECI143.4
- Price$0.60 / $2.20
- Context205K
Grok 4.3 is our pick
Grok 4.3 is the better all-round choice, scoring 67/100 against Kimi K2 Thinking (58) and GLM-4.7 (57). It leads on capability, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGrok 4.3Capabilities Index (ECI): Grok 4.3 149.9 · Kimi K2 Thinking 145.5 · GLM-4.7 143.4
- Lowest priceGLM-4.7GLM-4.7 $1.00 · Kimi K2 Thinking $1.07 · Grok 4.3 $1.56 per 1M tokens (3:1 blend)
- Longest contextGrok 4.3Grok 4.3 1,000,000 · Kimi K2 Thinking 262,144 · GLM-4.7 204,800 tokens
- Widest inputsGrok 4.3Kimi K2 Thinking: Text · Grok 4.3: Text, Images, PDFs · GLM-4.7: Text
- Self-hostingKimi K2 Thinking and GLM-4.7Publishes downloadable weights
| Measure | Weight | Kimi K2 Thinking | Grok 4.3 | GLM-4.7 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 73 | 77 | 71 |
| Price | 25% | 46 | 39 | 48 |
| Inputs & features | 15% | 35 | 80 | 35 |
| Context window | 10% | 43 | 64 | 39 |
| Overall | 100% | 58/100 | 67/100 | 57/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 145.5 | 149.9 (best) | 143.4 |
| ECI rank | #90 of 158 | #69 of 158 (best) | #99 of 158 |
| GPQA DiamondGraduate-level science questions | 84.2% | 88.8% (best) | 83.3% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 42.8% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 83.1% | 93.3% (best) | 83.3% |
| SimpleQA VerifiedShort factual questions | — | 33.2% (best) | 32.2% |
| Price per million tokens | |||
| Input | $0.60 (best) | $1.25 | $0.60 (best) |
| Output | $2.50 | $2.50 | $2.20 (best) |
| Cached input | — | $0.20 | $0.11 (best) |
| Blended (3:1) | $1.07 | $1.56 | $1.00 (best) |
| Long-context rate | Same rate | Over 200K: $2.50 / $5.00 | Same rate |
| Price source | Median of 14 providers | Official xAI API | Official Z.AI API |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 204,800 tokens |
| Max output | 262,144 tokens (best) | 30,000 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yeslow · medium · high · xhigh | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | grok-4.3 | glm-4.7 |
| API providers | 15 | 30 (best) | 30 (best) |
| Released | Nov 6, 2025 | Apr 17, 2026 | Dec 22, 2025 |
| Knowledge cutoff | Aug 2024 | — | 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.
Kimi K2 Thinking$11.00
Grok 4.3$17.50
GLM-4.7$10.40
Which should you choose?
Which is better: Kimi K2 Thinking, Grok 4.3 or GLM-4.7?
Grok 4.3 is the better all-round choice, scoring 67/100 against Kimi K2 Thinking (58) and GLM-4.7 (57). It leads on capability, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Kimi K2 Thinking, Grok 4.3 or GLM-4.7?
GLM-4.7 is cheaper at $0.60 input / $2.20 output per million tokens (official Z.AI API price). Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 14 API providers); Grok 4.3 costs $1.25 input / $2.50 output per million tokens (official xAI 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 $1.07 for Kimi K2 Thinking (1.1× as much) and $1.56 for Grok 4.3 (1.6× as much).
Which scores higher on benchmarks?
Grok 4.3 scores higher on the Capabilities Index (ECI): Grok 4.3 149.9 (#69 of 158), Kimi K2 Thinking 145.5 (#90 of 158) and GLM-4.7 143.4 (#99 of 158). Their confidence ranges do not overlap (147.9–151.9 vs 143.7–147.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — Grok 4.3 88.8%, Kimi K2 Thinking 84.2%, GLM-4.7 83.3%; OTIS Mock AIME 2024–2025 — Grok 4.3 93.3%, GLM-4.7 83.3%, Kimi K2 Thinking 83.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Thinking, Grok 4.3 and GLM-4.7 yet, so there is no like-for-like coding score. On overall capability, Grok 4.3 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?
Grok 4.3 has the largest context window at 1,000,000 tokens, against 262,144 for Kimi K2 Thinking and 204,800 for GLM-4.7. Maximum output per response: Kimi K2 Thinking up to 262,144, Grok 4.3 up to 30,000, GLM-4.7 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Kimi K2 Thinking accepts text; Grok 4.3 accepts text, images and PDFs; GLM-4.7 accepts text. Grok 4.3 handles the widest range of inputs.
Are any of these open source?
Kimi K2 Thinking and GLM-4.7 publishes its weights and can be self-hosted; Grok 4.3 is proprietary.
Which is newer?
Grok 4.3 is the newest, released Apr 17, 2026. GLM-4.7 came out Dec 22, 2025; Kimi K2 Thinking came out Nov 6, 2025. Knowledge cutoff: Kimi K2 Thinking Aug 2024, GLM-4.7 Apr 2025.
How do you decide the winner?
This rating uses 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 Nov 18, 2026.