GLM-4.6
Z AIOpen weightsMITReleased Sep 30, 2025
GLM-4.6 has no arena.ai Agents result yet, so on our leaderboard it is listed after models that do. GLM-4.6 ranks #127 on the LMArena Text leaderboard (style control) with an Arena score of 1424.3 (±3.9, 35,818 votes). Artificial Analysis Intelligence Index: 14.9. API price: $0.58 input / $2.20 output per 1M tokens. Context: 205K. Nearest rivals: Claude Haiku 5.5 (1424.6) above and Qwen3 Max (1423.5) below.
Quick answer
- Agents leaderboard
- No result yet
- Text (LMArena)
- #127 · 1424.3
- 17NAS overall
- #70 of 87
- API price (in / out)
- $0.58 / $2.20 per 1M tokens
- Closest rival
- Claude Haiku 5.5 · 1424.6
- Cheaper alternative
- DeepSeek V4 Flash: Text 1435.7, output $0.28 (87% cheaper)
- Data updated
- Oct 25, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| reasoning | 18.5 | 45.8 | – | – | – |
| non-reasoningUsed in table | 14.9 | – | – | – | – |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 66 |  Mistral Medium 3.5 | 1426.4 | 14.2 | $7.50 | 160 |
| 67 |  DeepSeek V3.2 | 1424.8 | 16.0 | $0.42 | – |
| 68 |  Claude Haiku 5.5 | 1424.6 | 43.4 | $0.50 | 242 |
| 69 | GLM-4.6This page | 1424.3 | 14.9 | $2.20 | – |
| 70 |  Qwen3 Max | 1423.5 | 15.6 | – | – |
More from Z AI
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 48 | GLM-5 | 1457.4 | 27.9 | $3.20 | – |
Pricing
- Official API list price: $0.58 input and $2.20 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $0.98 per 1M tokens.
- Among 82 models with an output price, it is the #22 cheapest.
- The cheapest OpenRouter route charges $0.55 input / $2.20 output.
Sources & methodology
GLM-4.6 has no arena.ai Agents result yet, so on our leaderboard it is listed after models that do.
- 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
What rank is GLM-4.6 right now?
GLM-4.6 is #69 on our leaderboard of 70 scored models (Arena score 1424.3); its raw LMArena rank is #127.
What does GLM-4.6 cost via API?
Input $0.58 / output $2.20 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 $0.98 per 1M tokens.
How close is GLM-4.6 to the models ranked next to it?
It is 0.3 points behind Claude Haiku 5.5 (1424.6) and 0.8 points ahead of Qwen3 Max (1423.5); gaps smaller than the confidence interval (±3.9) are not significant.
Is GLM-4.6 open source? Can it be self-hosted?
GLM-4.6 is an open-weights model (license: MIT); you can download the weights and self-host.
What is the context length of GLM-4.6?
205K (204,800 tokens, as listed on OpenRouter).
GLM-4.6 vs Claude Haiku 5.5: which is better?
On the LMArena Text leaderboard GLM-4.6 scores 1424.3 and Claude Haiku 5.5 scores 1424.6 (a 0.3-point gap, within the confidence interval, so not significant). On price, GLM-4.6 costs $2.20 and Claude Haiku 5.5 $0.50 per 1M output tokens.
Is there a cheaper model close to GLM-4.6?
Yes: DeepSeek V4 Flash scores 1435.7 on the Text leaderboard (GLM-4.6: 1424.3) and costs $0.28 per 1M output tokens, about 87% less than GLM-4.6 ($2.20).
Where does the GLM-4.6 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 25, 2026.