Models / DeepSeek V4 Pro 0813
DeepSeekDeepSeek V4 Pro 0813
11 published results from 1 source. Each card shows where the number comes from and what it does not measure. Results are never combined into one score.
- Provider
- DeepSeek
- Sources
- 1
- Our benchmarks
- 0
- Price
- Not yet published
Reported by others
-0.01
Confirmed task success · rank 17 of 46
- Unit
- IPS effect estimate, higher is better
- Range
- -0.05 to 0.03
- Sample
- 3825 observations
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 28 Sep 2026
- Not shown
- Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
0.03
Praise over complaint · rank 9 of 46
- Unit
- IPS effect estimate, higher is better
- Range
- -0.03 to 0.09
- Sample
- 1331 observations
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 28 Sep 2026
- Not shown
- Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
0.02
Steerability · rank 6 of 46
- Unit
- IPS effect estimate, higher is better
- Range
- -0.02 to 0.06
- Sample
- 4237 observations
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 28 Sep 2026
- Not shown
- Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
0.00
Tool grounding · rank 1 of 46
- Unit
- IPS effect estimate, higher is better
- Range
- 0.00 to 0.00
- Sample
- 728204 observations
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 28 Sep 2026
- Not shown
- Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
1,453
Overall · rank 41 of 177
- Unit
- Arena rating, higher is better
- Range
- 1,448 to 1,459
- Sample
- 9750 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.
1,467
Business, management and finance · rank 11 of 402
- Unit
- Arena rating, higher is better
- Range
- 1,453 to 1,481
- Sample
- 1820 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,446
Creative writing · rank 18 of 407
- Unit
- Arena rating, higher is better
- Range
- 1,432 to 1,460
- Sample
- 2001 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,485
Expert prompts · rank 20 of 359
- Unit
- Arena rating, higher is better
- Range
- 1,466 to 1,503
- Sample
- 1026 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,461
Instruction following · rank 20 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,451 to 1,471
- Sample
- 3489 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,464
Overall · rank 30 of 409
- Unit
- Arena rating, higher is better
- Range
- 1,458 to 1,471
- Sample
- 9857 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
1,454
Writing, literature and language · rank 17 of 408
- Unit
- Arena rating, higher is better
- Range
- 1,442 to 1,466
- Sample
- 2656 votes
- Configuration
- DeepSeek V4 Pro 0813
- Measured
- 25 Sep 2026
- Not shown
- Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.
