ERNIE 5.0 Thinking Preview
Context
n/a
Max output
n/a
Serving providers
0
Cheapest input
n/a /1M
Benchmarks
independent evaluations · source: Artificial AnalysisHeadline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 1% | default | — | |
| GPQA Diamond | 78% | default | — | |
| Humanity's Last Exam | 13% | default | — | |
| IFBench | 41% | default | — | |
| LiveCodeBenchArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 81% | — | — | |
| Long-Context ReasoningArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 7% | — | — | |
| MMLU-ProFrozen Aug 18, 2026 | 83% | default | — | |
| MMMU-Pro | 65% | default | — | |
| Omniscience | -45.6 | default | — | |
| Omniscience Accuracy | 0.2 | default | — | |
| Omniscience Non Hallucination | 0.1 | default | — | |
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 38% | — | — | |
| TerminalBench Hard | 25% | default | — | |
| τ²-bench | 84% | default | — |
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
availabilityNo public price yet. Not offered on-demand at any tracked provider.
Price history
listed seller prices, input and output per 1M tokens Input Output
Price history is accruing. We record a point each day a listed seller price changes; the full backfill lands shortly.
Other Baidu models
compare pricing across the Baidu lineupErnie 4.5 VL 424B A47b$0.42/1M · 2 providersErnie 4.5 21B A3b$0.07/1M · 1 providerErnie 4.5 21B A3b Thinking$0.07/1M · 1 providerErnie 4.5 21B A3b Pt$0.10/1M · 1 providerErnie 4.5 300B A47b Pt$0.10/1M · 1 providerErnie 4.5 VL 28B A3b$0.14/1M · 1 providerErnie 4.5 300B A47b Paddle$0.28/1M · 1 providerErnie 4.5 VL 28B A3b Thinking$0.39/1M · 1 provider
Listed prices from LiteLLM, OpenRouter and Vercel
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI