GLM-4.7 vs Claude Haiku 4.5 vs Kimi K2 Instruct

It is close. Our weighted score puts them within 2 points (Claude Haiku 4.5 57/100, GLM-4.7 55/100, Kimi K2 Instruct 50/100), so choose by what matters most for your work: GLM-4.7 for raw capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

GLM-4.7 is cheaper at $0.60 input / $2.20 output per million tokens (official Z.AI API price). Kimi K2 Instruct costs $0.57 input / $2.30 output per million tokens (median across 11 API providers); 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 $1.00 for Kimi K2 Instruct (1× as much) and $2.00 for Claude Haiku 4.5 (2× as much).

GLM-4.7 scores higher on the Capabilities Index (ECI): GLM-4.7 143.7 (#94 of 165), Claude Haiku 4.5 142.2 (#102 of 165) and Kimi K2 Instruct 139.9 (#112 of 165). The confidence ranges of the top two overlap (141.4–145.8 vs 139.4–143.9), so treat the gap as small.

There are no published SWE-bench Verified results for GLM-4.7, Claude Haiku 4.5 and Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, GLM-4.7 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

GLM-4.7 has the largest context window at 204,800 tokens, against 200,000 for Claude Haiku 4.5 and 131,072 for Kimi K2 Instruct. Maximum output per response: GLM-4.7 up to 131,072, Claude Haiku 4.5 up to 64,000, Kimi K2 Instruct up to 32,768 tokens.

GLM-4.7 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; Kimi K2 Instruct accepts text. Claude Haiku 4.5 handles the widest range of inputs.

GLM-4.7 and Kimi K2 Instruct publishes its weights (Modified MIT) and can be self-hosted; Claude Haiku 4.5 is proprietary.

GLM-4.7 is the newest, released Dec 22, 2025. Claude Haiku 4.5 came out Oct 15, 2025; Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: GLM-4.7 Apr 2025, Claude Haiku 4.5 Feb 28, 2025.

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 Nov 2, 2026.