Decision support
Claude Sonnet 4 vs ERNIE 4.5 Turbo
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Baidu
Benchmark results
Arena Text
Arena rating · Higher is better
- Claude Sonnet 41402Arena #165CI 1397 to 1406
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default140232K, thinking · 95% CI 1397 to 1406 · 34,078 votes
- default139195% CI 1387 to 1395 · 39,126 votes
ERNIE 4.5 TurboNot reported
Arena Vision
Arena rating · Higher is better
- Claude Sonnet 41206Arena #90CI 1189 to 1223
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default120632K, thinking · 95% CI 1189 to 1223 · 1,141 votes
- default118995% CI 1174 to 1203 · 1,803 votes
ERNIE 4.5 TurboNot reported
ARC-AGI-2
Best published score · Higher is better
- Claude Sonnet 45.9%#60 of 85
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default5.9%16K
- default2.1%8K
- default1.3%
- default0.8%1K
ERNIE 4.5 TurboNot reported
Source:External evaluation via Epoch AIOriginal-source terms applyFrontierMath-2025-02-28-Private
Best published score · Higher is better
- Claude Sonnet 44.1%#44 of 58
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default4.1%
ERNIE 4.5 TurboNot reported
Source:Epoch AI evaluationFrontierMath-Tier-4-2025-07-01-Private
Best published score · Higher is better
- Claude Sonnet 40.0%#39 of 46
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default0.0%
ERNIE 4.5 TurboNot reported
Source:Epoch AI evaluationGPQA diamond
Best published score · Higher is better
- Claude Sonnet 479.2%#89 of 161
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default79.2%59K
- default78.3%32K
- default75.8%16K
- default66.7%
ERNIE 4.5 TurboNot reported
Source:Epoch AI evaluationHumanity's Last Exam
Best published score · Higher is better
- Claude Sonnet 45.5%#30 of 34
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- unknown5.5%
ERNIE 4.5 TurboNot reported
Source:External evaluation via Epoch AIOriginal-source terms applyOSWorld
Best published score · Higher is better
- Claude Sonnet 443.9%#7 of 10
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default43.9%claude-4-sonnet-20250514 (50 steps)
- default41.4%claude-4-sonnet-20250514 (100 steps)
- default31.2%claude-4-sonnet-20250514 (15 steps)
ERNIE 4.5 TurboNot reported
Source:OS World WebsiteOriginal-source terms applyOTIS Mock AIME 2024-2025
Best published score · Higher is better
- Claude Sonnet 471.1%#91 of 158
- ERNIE 4.5 TurboNot reported
Runs and sources
Claude Sonnet 4- default71.1%32K
- default68.9%59K
- default53.3%16K
- default28.9%
ERNIE 4.5 TurboNot reported
Source:Epoch AI evaluation
Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.
Original-source terms apply to evaluations credited to their original publishers.
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.
Model specifications
API pricing · USD per 1M tokens
Capabilities and modalities
Architecture and availability
A dash means the field is not reported. Provider-specific performance and pricing may differ.