Claude Haiku 4.5 vs GLM-5

Claude Haiku 4.5 is the better all-round choice, scoring 58/100 against GLM-5 (55). It leads on inputs & features. GLM-5 wins on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

GLM-5 is cheaper at $1.00 input / $3.20 output per million tokens (official Z.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 $1.55 per million tokens for GLM-5 versus $2.00 for Claude Haiku 4.5 (1.3× as much).

GLM-5 scores higher on the Capabilities Index (ECI): GLM-5 145.8 (#74 of 148) and Claude Haiku 4.5 142.4 (#90 of 148). The confidence ranges of the top two overlap (143.9–147.7 vs 139.5–144.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — GLM-5 80.0%, Claude Haiku 4.5 66.7%.

There are no published SWE-bench Verified results for Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, GLM-5 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

GLM-5 has the largest context window at 204,800 tokens, against 200,000 for Claude Haiku 4.5. Maximum output per response: Claude Haiku 4.5 up to 64,000, GLM-5 up to 131,072 tokens.

Claude Haiku 4.5 accepts text, images and PDFs; GLM-5 accepts text. Claude Haiku 4.5 handles the widest range of inputs.

GLM-5 publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.

GLM-5 is the newest, released Feb 12, 2026. Claude Haiku 4.5 came out Oct 15, 2025. Knowledge cutoff: 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 Oct 4, 2026.