GLM-4.7 vs Claude Haiku 4.5 vs Kimi K2 Thinking

It is close. Our weighted score puts them within a point (Claude Haiku 4.5 58/100, Kimi K2 Thinking 58/100, GLM-4.7 56/100), so choose by what matters most for your work: Kimi K2 Thinking for raw capability and GLM-4.7 on price. 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 Thinking costs $0.60 input / $2.50 output per million tokens (median across 10 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 $1.07 for Kimi K2 Thinking (1.1× as much) and $2.00 for Claude Haiku 4.5 (2× as much).

Kimi K2 Thinking scores higher on the Capabilities Index (ECI): Kimi K2 Thinking 146.0 (#72 of 148), GLM-4.7 143.5 (#84 of 148) and Claude Haiku 4.5 142.4 (#90 of 148). The confidence ranges of the top two overlap (143.4–147.6 vs 141.3–145.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2 Thinking 84.2%, GLM-4.7 83.3%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — GLM-4.7 83.3%, Kimi K2 Thinking 83.1%, Claude Haiku 4.5 66.7%.

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

Kimi K2 Thinking 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 Thinking up to 262,144 tokens.

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

GLM-4.7 and Kimi K2 Thinking publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.

GLM-4.7 is the newest, released Dec 22, 2025. Kimi K2 Thinking came out Nov 6, 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 Thinking Aug 2024.

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.