GLM 4.6 Original
GLM-4.6, Zhipu's flagship text model with 256K context window and advanced reasoning capabilities. Direct via Z-AI (Zhipu).
- Reasoning
Added Dec 11, 2025
Pricing
Auto routing · per 1M tokens- Input
- $0.55
- Output
- $2.20
- Cache read
- $0.11
Specifications
- Context window
- 256K
- Max output
- 65.5K
- Parameters
- 357B / 32B
- Total / active
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1424.5
Overall Rank
#127 / 421
Votes
35,631
Confidence Interval
1420.6 - 1428.4
Category Scores
Coding
#149 / 416
7,577 votes
1458.2
Math
#133 / 404
2,131 votes
1417.8
Longer Query
#129 / 399
9,080 votes
1431.6
Creative Writing
#110 / 419
5,089 votes
1401.1
Instruction Following
#132 / 421
10,221 votes
1412.8
Hard Prompts
#132 / 421
19,345 votes
1441.9
Additional Categories22
Chinese
#98 / 395
2,690 votes
1477.8
German
#110 / 320
681 votes
1426.4
Korean
#110 / 289
612 votes
1378.4
French
#113 / 301
702 votes
1447.4
Industry Mathematical
#113 / 402
1,752 votes
1437.6
Polish
#114 / 243
1,300 votes
1419.8
Industry Medicine And Healthcare
#119 / 391
1,921 votes
1448.2
Japanese
#121 / 288
372 votes
1370.8
Industry Entertainment And Sports And Media
#122 / 419
6,632 votes
1395.3
Industry Legal And Government
#123 / 393
2,438 votes
1435.8
Industry Writing And Literature And Language
#123 / 420
8,020 votes
1404.9
Industry Life And Physical And Social Science
#124 / 419
5,903 votes
1446.0
English
#126 / 421
15,222 votes
1437.1
Exclude Ties
#126 / 421
24,988 votes
1416.2
Non English
#128 / 421
20,373 votes
1407.7
Hard Prompts English
#131 / 419
8,205 votes
1449.5
Spanish
#131 / 304
1,008 votes
1413.3
Multi Turn
#135 / 419
5,600 votes
1421.0
Expert
#139 / 371
2,052 votes
1440.1
Russian
#141 / 385
3,520 votes
1407.0
Industry Software And It Services
#144 / 421
12,558 votes
1453.0
Industry Business And Management And Financial Operations
#148 / 414
6,879 votes
1412.1
Published 2026-11-11 · Matched as GLM-4.6 · CC BY 4.0
LMArena DatasetLeaderboard results
These leaderboards tested GLM 4.6, another version of this model.
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Creative Writing v3 | 1412 | #66 of 91 |
Longform Writing | 57.3 | #61 of 93 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 49.8 | #40 of 125 |
UGI Willingness | 4.2 | #44 of 125 |
UGI Writing | 53.3 | #53 of 125 |
Filtered and ranked to models on NanoGPT.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.55 | $2.20 | $0.11 | N/A | N/A | |
| $0.55 | $2.20 | $0.11 | N/A | N/A | |
| $0.472 | $2.00 | N/A | N/A | N/A | |
| $0.525 | $2.10 | $0.105 | N/A | N/A | |
| $0.578 | $2.31 | $0.116 | N/A | N/A | |
| $0.63 | $2.31 | $0.116 | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.