GLM-4.6-FP8: benchmark scores, price and ranking
GLM-4.6-FP8 from zai-org ranks #152 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.0), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- zai-org
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #152 of 743 (score 51.0)
Across the 1 benchmark where at least ten models are scored, GLM-4.6-FP8 is in the top 10% on 0 and in the top half on 1.
GLM-4.6-FP8 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 81.3% | #100 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About GLM-4.6-FP8
GLM-4.6-FP8 is an open-weight model that can run on your own hardware from zai-org. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where GLM-4.6-FP8 stands
On our aggregate score, GLM-4.6-FP8 is #152 of 743 ranked models, in the top quarter. Its score is 51.0; the scale is centred on 50, so it sits 1.0 points above the typical model. That beats 80% of the ranked field. Among the 6 ranked zai-org models it is #4. The next one up is GLM-5.1-FP8 at 51.2. The next one down is glm-4.7-flash at 50.1.
GLM-4.6-FP8, benchmark by benchmark
GPQA Diamond puts GLM-4.6-FP8 at 81.3%, #100 of 275. That beats 64% of the models tested, but 14.5 points short of GPT-6 Astra (max) (95.8%). The results either side are o3 (high) (81.8%) and MiniMax-M2.1 (80.8%). It covers expert-level science questions. The board median is 71.7%, so GLM-4.6-FP8 is 9.6 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: HuggingFace GPQA Diamond leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #149 Quasar Alpha (51.0)
- #150 ERNIE-4.5-300B-A47B-PT (51.0)
- #151 LongCat-Flash-Lite (51.0)
- #153 Claude 4 Opus (51.0)
- #154 Gemini 2.5 Pro Preview (Mar 2025) (50.9)
- #155 claude-sonnet-4-20250514_59K (50.9)
More from zai-org
- GLM-4.7-FP8 (#105, 51.6)
- GLM-5-FP8 (#126, 51.4)
- GLM-5.1-FP8 (#141, 51.2)
- glm-4.7-flash (#215, 50.1)
- glm-4-9b (#480, 46.9)
Compare it on the live leaderboard → · How the aggregate score works