GLM 4.7 Flash
GLM-4.7-Flash is a lightweight 30B model optimized for coding and agentic tasks. Balances high performance with efficiency.
- Reasoning
- Tool Calling
- Structured Output
Added Jan 19, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.0605
- Output
- $0.40
- Cache read
- $0.0303
Specifications
- Context window
- 200K
- Max output
- 128K
- Parameters
- 30B / 3B
- Total / active
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1364.5
Overall Rank
#206 / 421
Votes
11,932
Confidence Interval
1358.8 - 1370.3
Category Scores
Coding
#198 / 416
2,782 votes
1422.9
Math
#209 / 404
750 votes
1361.6
Longer Query
#208 / 399
3,353 votes
1370.2
Creative Writing
#234 / 419
1,855 votes
1304.8
Instruction Following
#212 / 421
3,279 votes
1347.2
Hard Prompts
#205 / 421
6,696 votes
1384.3
Additional Categories21
Chinese
#180 / 395
817 votes
1410.4
Korean
#186 / 289
235 votes
1301.2
German
#189 / 320
227 votes
1341.6
Industry Software And It Services
#189 / 421
4,265 votes
1419.8
English
#195 / 421
4,614 votes
1391.0
Industry Mathematical
#197 / 402
507 votes
1378.7
Spanish
#198 / 304
436 votes
1364.8
Expert
#200 / 371
880 votes
1388.0
Industry Business And Management And Financial Operations
#200 / 414
2,231 votes
1368.4
Hard Prompts English
#201 / 419
2,540 votes
1401.6
Multi Turn
#206 / 419
2,129 votes
1359.1
French
#207 / 301
261 votes
1355.7
Industry Legal And Government
#207 / 393
865 votes
1378.5
Industry Life And Physical And Social Science
#208 / 419
1,866 votes
1380.6
Exclude Ties
#211 / 421
8,266 votes
1326.2
Non English
#213 / 421
7,318 votes
1340.8
Russian
#217 / 385
1,711 votes
1344.1
Industry Entertainment And Sports And Media
#219 / 419
2,121 votes
1316.1
Industry Medicine And Healthcare
#219 / 391
839 votes
1369.8
Polish
#219 / 243
316 votes
1294.9
Industry Writing And Literature And Language
#224 / 420
2,638 votes
1330.3
Published 2026-11-11 · Matched as GLM-4.7-Flash · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 18, 2026 | ||
GPQA Diamond | 60.5% | #99 of 117 |
OTIS Mock AIME 2024–2025 | 58.3% | #100 of 119 |
Creative Writing v3 | 1139 | #77 of 91 |
Longform Writing | 47.8 | #72 of 93 |
EQ-Bench 3 | 1118 | #30 of 45 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 33.8 | #83 of 125 |
UGI Willingness | 6.8 | #9 of 125 |
UGI Writing | 25.0 | #116 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)
| $0.0605 | $0.40 | $0.0303 | N/A | N/A | |
| $0.0605 | $0.40 | $0.0303 | N/A | N/A | |
| $0.0635 | $0.42 | N/A | N/A | N/A | |
| $0.0735 | $0.428 | $0.015 | N/A | N/A | |
| $0.0735 | $0.42 | $0.0105 | 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.