BaiduOpen weightsERNIE 4.5
Best configuration ranks #406 of 610 on the BenchLeader Index at 44.8 ±2.8. Released 2 Jul 2025.
- Blended price
- $0.485/M
- $0.280 in · $1.10 out
- Output speed
- –
- First answer
- –
- Context
- 131k
- Overall index45
- Reasoning42
- Agents & tools39
- Knowledge47
- Instruction following42
- Composite38
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 81.1%#178 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 3.3%#511 | Artificial Analysis |
| Kagi LLM Benchmark | 45.0%#92 | Kagi LLM Benchmark |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 6.1%#257 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 0.0%#375 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -35.1#233 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 39.1%#261 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 7.5#391 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.0040 | – | – |
| Code edit | 6,000 / 1,500 | $0.0033 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.021 | – | – |
| Structured extraction | 2,000 / 200 | $0.0008 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.