GLM-5.3 Flash
Z.AIOpen weightsMITReleased Aug 26, 2026
On the arena.ai Agents leaderboard, GLM-5.3 Flash has a task success rate of -1.09% (—, rank #33, 95% interval -1.76%–-0.42%). GLM-5.3 Flash ranks #41 on the LMArena Text leaderboard (style control) with an Arena score of 1473.8 (±4.9, 32,925 votes). Artificial Analysis Intelligence Index: 41.8. API price: $0.15 input / $0.50 output per 1M tokens. Context: 1.05M. Nearest rivals: Qwen3.7 Max (1474.3) above and Gemini 3 Flash (1472.8) below.
Quick answer
- Agents leaderboard
- #33 of 48 · -1.09% success
- Text (LMArena)
- #41 · 1473.8
- 17NAS overall
- #33 of 84
- API price (in / out)
- $0.15 / $0.50 per 1M tokens
- Closest rival
- Qwen3.7 Max · 1474.3
- Data updated
- Oct 16, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 31 |  Claude Sonnet 5.5 | 1474.9 | 56.0 | $10.00 | 142 |
| 32 |  DeepSeek V4.1 Flash | 1474.6 | 39.5 | $1.20 | 180 |
| 33 |  Qwen3.7 Max | 1474.3 | 29.5 | $7.50 | – |
| 34 | GLM-5.3 FlashThis page | 1473.8 | 41.8 | $0.50 | 63 |
| 35 |  Gemini 3 Flash | 1472.8 | 17.9 | $3.00 | – |
| 36 | Claude Sonnet 4.6 | 1472.1 | 24.7 | $15.00 | – |
| 37 |  Grok 4.20 | 1471.5 | 25.7 | $2.50 | – |
More from Z.AI
Pricing
- Official API list price: $0.15 input and $0.50 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $0.24 per 1M tokens.
- Among 79 models with an output price, it is the #6 cheapest.
- The cheapest OpenRouter route charges $0.021 input / $0.90 output. That route is over 60% below list price — usually a promotion or a single provider, so check its reliability.
Sources & methodology
On the arena.ai Agents leaderboard, GLM-5.3 Flash has a task success rate of -1.09% (—, rank #33, 95% interval -1.76%–-0.42%).
- arena.ai Agents — agent task success rate, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does GLM-5.3 Flash do on the Agents leaderboard?
On the arena.ai Agents leaderboard, GLM-5.3 Flash has a task success rate of -1.09% (—, rank #33, 95% interval -1.76%–-0.42%).
What rank is GLM-5.3 Flash right now?
GLM-5.3 Flash is #34 on our leaderboard of 69 scored models (Arena score 1473.8); its raw LMArena rank is #41.
What does GLM-5.3 Flash cost via API?
Input $0.15 / output $0.50 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $0.24 per 1M tokens.
How fast is GLM-5.3 Flash?
Artificial Analysis measures about 63 output tokens per second, 2.4 s to the first token and 34 s to the first answer token; it is a reasoning model, so latency includes thinking time.
How close is GLM-5.3 Flash to the models ranked next to it?
It is 0.5 points behind Qwen3.7 Max (1474.3) and 1.0 points ahead of Gemini 3 Flash (1472.8); gaps smaller than the confidence interval (±4.9) are not significant.
Is GLM-5.3 Flash open source? Can it be self-hosted?
GLM-5.3 Flash is an open-weights model (license: MIT); you can download the weights and self-host.
What is the context length of GLM-5.3 Flash?
1.05M (1,048,576 tokens, as listed on OpenRouter).
GLM-5.3 Flash vs Qwen3.7 Max: which is better?
On the LMArena Text leaderboard GLM-5.3 Flash scores 1473.8 and Qwen3.7 Max scores 1474.3 (a 0.5-point gap, within the confidence interval, so not significant). Agent task success: GLM-5.3 Flash -1.09%, Qwen3.7 Max -5.80%. On price, GLM-5.3 Flash costs $0.50 and Qwen3.7 Max $7.50 per 1M output tokens.
Is there a cheaper model close to GLM-5.3 Flash?
Among models within 15 Text points, none is currently more than 30% cheaper than GLM-5.3 Flash on output price.
Where does the GLM-5.3 Flash data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Oct 16, 2026.