DeepSeek Chat 0324
DeepSeek V3 0324, DeepSeek's 03 March 2025 V3 model, optimized for general-purpose tasks. Quantized at FP8.
- Tool Calling
- Structured Output
Pricing
Auto routing · per 1M tokens- Input
- $0.20
- Output
- $0.77
- Cache read
- $0.135
Specifications
- Context window
- 128K
- Max output
- 8.2K
- Parameters
- 671B / 37B
- Total / active
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1395.3
Overall Rank
#172 / 421
Votes
44,915
Confidence Interval
1391.4 - 1399.2
Category Scores
Coding
#193 / 416
8,319 votes
1428.0
Math
#203 / 404
3,156 votes
1366.5
Longer Query
#183 / 399
8,523 votes
1393.7
Creative Writing
#130 / 419
5,982 votes
1389.8
Instruction Following
#183 / 421
12,389 votes
1377.8
Hard Prompts
#184 / 421
18,559 votes
1408.1
Additional Categories22
Industry Entertainment And Sports And Media
#141 / 419
8,000 votes
1383.1
German
#144 / 320
1,224 votes
1391.7
Polish
#144 / 243
2,733 votes
1395.9
Japanese
#145 / 288
1,056 votes
1343.7
Multi Turn
#154 / 419
7,673 votes
1410.4
Industry Writing And Literature And Language
#155 / 420
10,270 votes
1386.4
Russian
#155 / 385
3,569 votes
1400.4
French
#157 / 301
593 votes
1415.4
Industry Medicine And Healthcare
#158 / 391
2,657 votes
1427.0
Korean
#158 / 289
964 votes
1339.2
Industry Legal And Government
#159 / 393
2,906 votes
1409.5
Exclude Ties
#172 / 421
31,418 votes
1376.0
Industry Life And Physical And Social Science
#172 / 419
7,619 votes
1414.1
Non English
#173 / 421
23,526 votes
1378.8
English
#175 / 421
21,384 votes
1408.6
Chinese
#176 / 395
3,033 votes
1415.3
Industry Business And Management And Financial Operations
#179 / 414
6,851 votes
1389.2
Spanish
#181 / 304
983 votes
1376.6
Hard Prompts English
#182 / 419
8,999 votes
1419.8
Industry Software And It Services
#183 / 421
14,336 votes
1422.8
Expert
#190 / 371
2,341 votes
1396.2
Industry Mathematical
#213 / 402
2,933 votes
1364.6
Published 2026-11-11 · Matched as DeepSeek-V3 (0324) · 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 15, 2026 | ||
GPQA Diamond | 67.6% | #93 of 119 |
OTIS Mock AIME 2024–2025 | 37.8% | #106 of 121 |
Creative Writing v3 | 1472 | #61 of 96 |
Longform Writing | 60.1 | #55 of 97 |
EQ-Bench 3 | 1124 | #32 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 55.0 | #23 of 149 |
UGI Willingness | 5.8 | #30 of 149 |
UGI Writing | 49.1 | #61 of 149 |
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)
| $0.20 | $0.77 | $0.135 | N/A | N/A | |
| $0.20 | $0.77 | $0.135 | N/A | N/A | |
| $0.263 | $1.05 | N/A | N/A | N/A | |
| $0.298 | $1.18 | N/A | N/A | N/A | |
| $0.305 | $1.20 | $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.