GLM-5.3-Flash
GLM-5.3-Flash (Z.ai (Zhipu AI)) was released on Aug 20, 2026. In the Epoch AI capability ranking (ECI), it ranks #44 out of 267 models, with 153.23. On Arena, which measures human preference in blind comparisons, it has 1,528 ELO points (#24). On LiveBench, the overall average is 71.6, #46 out of 58 scored models. Against models of the same generation, its best result is on Btf3: 14.9%, #1 of 8, tied with 1 others.
Where GLM-5.3-Flash stands out and where it falls behind, by the numbers
GLM-5.3-Flash has published results on 20 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Nov 23, 2025 and Nov 18, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 20 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 90.2% | #37 / 78 (tied with 1) | #38 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 93.9% | #44 / 80 | #44 / 168 | 100.0% GPT-5.5 |
| CritPt | 15.4% | #36 / 77 (tied with 1) | #36 / 112 | 32.3% GPT-5.6 Sol |
| SciCode | 51.6% | #42 / 75 | #42 / 104 | 66.9% Claude Opus 5.5 |
| Frontiermath Tiers 1 3 V2 | 55.8% | #45 / 68 | #45 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI 2 | 65.8% | #23 / 48 | #23 / 83 | 95.0% GPT-6 Astra |
| WebDev Arena | 1,607 | #19 / 72 | #19 / 82 | 1,820 Claude Opus 5.5 |
| ARC-AGI | 91.0% | #24 / 48 | #24 / 81 | 98.5% Claude Fable 5 |
| Chess puzzles | 21.0% | #48 / 63 (tied with 4) | #55 / 80 | 76.0% GPT-6 Astra |
| Game puzzles | 8.0% | #57 / 61 (tied with 1) | #67 / 77 | 84.0% GPT-6 Astra |
| ProofBench | 21.0% | #47 / 69 (tied with 1) | #47 / 74 | 100.0% Claude Fable 5.1 |
| Frontiermath Tier 4 V2 | 17.1% | #45 / 58 (tied with 4) | #47 / 67 | 100.0% GPT-6.1 Sol |
| Apex Agents | 52.8% | #23 / 49 | #23 / 50 | 82.4% Gemini 4 Argon |
| FrontierCode | 31.8% | #30 / 43 | #30 / 43 | 54.6% Claude Opus 5.5 |
| Gdp Pdf | 14.0% | #30 / 37 (tied with 3) | #30 / 37 | 35.0% GPT-6.1 Sol |
| DeepSWE | 63.4% | #13 / 26 | #13 / 26 | 74.1% GPT-6 Astra |
| Surface Evolver Bench | 52.5% | #14 / 23 (tied with 1) | #14 / 24 | 95.0% Claude Fable 5 |
| FrontierSWE | 18.1% | #17 / 20 | #17 / 20 | 65.5% GPT-6 Astra |
| CursorBench | 36.8% | #14 / 16 | #14 / 16 | 57.8% Claude Opus 5.5 |
| Btf3 | 14.9% | #1 / 8 (tied with 1) | #1 / 8 | 14.9% GLM-5.3 |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare GLM-5.3-Flash with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| Gemini 3.6 Flash | Google DeepMind | 154.24 | 1,530 | 73.6 | Jul 21, 2026 |
| Muse Spark 1.1 | Meta AI | 154.00 | 1,516 | 75.3 | Jul 9, 2026 |
| Grok 4.5 | xAI | 153.93 | 1,495 | 75.8 | Jul 8, 2026 |
| Qwen3.7-Max | Alibaba | 153.83 | 1,530 | 73.1 | May 19, 2026 |
| GPT-5.2 | OpenAI | 153.46 | 1,454 | 74.6 | Dec 11, 2025 |
| GLM-5.3-Flash | Z.ai (Zhipu AI) | 153.23 | 1,528 | 71.6 | Aug 20, 2026 |
| Claude Sonnet 4.6 | Anthropic | 152.39 | 1,504 | 73.0 | Feb 17, 2026 |
GLM-5.3-Flash or GPT-5.2?
GPT-5.2 is the model from another lab closest to GLM-5.3-Flash in capability. Across the 10 tests both took, this is the score:
| Test | GLM-5.3-Flash | GPT-5.2 |
|---|---|---|
| Game puzzles | 8.0% | 23.0% |
| Chess puzzles | 21.0% | 48.0% |
| Frontiermath Tier 4 V2 | 17.1% | 31.7% |
| ProofBench | 21.0% | 15.0% |
| ARC-AGI 2 | 65.8% | 52.9% |
| Frontiermath Tiers 1 3 V2 | 55.8% | 67.4% |
| WebDev Arena | 1,607 | 1,480 |
| ARC-AGI | 91.0% | 86.2% |
| AIME 2024 and 2025 (OTIS) | 93.9% | 96.1% |
| GPQA Diamond | 90.2% | 91.4% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
What GLM-5.3-Flash costs to deliver each task
Price per token is what is on the price sheet; cost per task is what lands on the invoice, because it depends on how many tokens the model spends. Each point is an effort level, published by whoever ran the test and compiled by Epoch AI. The further up and to the left, the more score per dollar.
CursorBench
The score scale does not start at zero.
Other models from Z.ai (Zhipu AI)
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| GLM-5.3-Flash | Aug 20, 2026 | 153.23 | 1,528 | 71.6 | Open weights (unrestricted) |
| GLM-5.3 | Aug 14, 2026 | 155.91 | n/a | 76.1 | API access |
| GLM-5.2 | Jun 16, 2026 | 151.86 | n/a | 73.2 | Open weights (unrestricted) |
| GLM-5.1 | Apr 7, 2026 | 149.99 | 1,514 | n/a | Open weights (unrestricted) |
| GLM-5 | Feb 11, 2026 | 145.78 | 1,511 | n/a | Open weights (unrestricted) |
| GLM-4.7 | Dec 22, 2025 | 143.79 | 1,495 | n/a | Open weights (unrestricted) |
| GLM-4.6 | Sep 30, 2025 | 140.78 | 1,500 | n/a | Open weights (unrestricted) |
Have you used GLM-5.3-Flash? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about GLM-5.3-Flash
Where does GLM-5.3-Flash rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, GLM-5.3-Flash ranks #44 out of 267 models, with an ECI of 153.23. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is GLM-5.3-Flash better than GPT-5.2?
Across the 10 tests both models took and Epoch AI compiled, GLM-5.3-Flash comes out ahead on 4, behind on 6 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
What is GLM-5.3-Flash best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of GLM-5.3-Flash are: Btf3 (#1 of 8); WebDev Arena (#19 of 72). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking