ERNIE-Light-DT-1.0
Launch tracker · day 12
ERNIE-Light-DT-1.0 at launch: the first independent results
As of 22 Nov 2026, ERNIE-Light-DT-1.0 (Baidu, first listed 11 Nov 2026) has independent results from DuelLab GameBench 2 (GameBench 2 by reasoning setting 43.7). It has no BenchLeader Index yet: the Index needs at least five independent results across two categories. It is listed at $1.13 in / $3.94 out per 1M tokens, with a 1M-token context window. Not yet measured by Artificial Analysis, LMArena, Epoch AI, Vals AI, LiveBench, ARC Prize, Scale AI and SWE-bench.
- First listed
- 11 Nov 2026 (day 12)
- Provider
- Baidu
- Price
- $1.13 in / $3.94 out per 1M tokens
- Context window
- 1M tokens
- Open weights
- Not stated
- BenchLeader Index
- Not yet (needs five results in two categories)
| Independent board | Results so far |
|---|---|
| DuelLab GameBench 2 | GameBench 2 by reasoning setting 43.7 |
Boards usually post results within days of a launch; this page is rebuilt every three hours.
Scores from independent publishers only; benchmark figures a provider publishes about its own model are not shown.
Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.
No cheaper ranked model scores higher: it is on the price frontier.
As of 22 Nov 2026, ERNIE-Light-DT-1.0 by Baidu is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $1.13 per 1M input tokens and $3.94 per 1M output tokens ($1.83 blended at 3:1), list price on 22 Nov 2026. It streams about 89 tokens/s (OpenRouter).
Key facts (as of 22 Nov 2026)
- ERNIE-Light-DT-1.0 API pricing: $1.13 per 1M input tokens and $3.94 per 1M output tokens ($1.83 blended at 3:1) (list price, 22 Nov 2026).
- ERNIE-Light-DT-1.0 streams about 89 tokens/s (OpenRouter, 22 Nov 2026).
In detail. ERNIE-Light-DT-1.0 is a Baidu model. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $1.83 per million tokens blended it is pricier than most ranked models. Output speed of 89 tokens per second puts it faster than most, with a first token in 1.0 s.
- Blended price
- $1.83/M
- $1.13 in · $3.94 out
- via OpenRouter
- Output speed
- 89 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.98 s
- Context
- 1.0M
- via OpenRouter
- Accepts
- Text
- via models.dev, OpenRouter
- Cost per task
- –
- Tokens per task
- –
- Released
- –
- date not published by our sources
Benchmark results
See all LLM benchmarks. 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.
Coding
| Benchmark | no reasoning | Source | Trend |
|---|---|---|---|
| GameBench 2 by reasoning settingnot in index | 43.7#147 | DuelLab GameBench 2 |
GameBench 2, best reasoning setting (None): 43.7. Reference only, not part of the BenchLeader Index.
DuelLab GameBench 2, release gb2-20261119-1d7fd529faf6 (https://benchmarks.duellab.org/releases/gb2-20261119-1d7fd529faf6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Baidu Qianfan | 97 tok/s | 0.98 s | $1.13 | $3.94 | 1.0M | – |
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 at $0.113 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0016 | $0.0013 | 4.3 s |
| Summarize a 30-page report | 12,000 / 600 | $0.016 | $0.0068 | 7.7 s |
| Code edit | 6,000 / 1,500 | $0.013 | $0.0081 | 17.8 s |
| Agentic coding session | 60,000 / 4,000 | $0.084 | $0.038 | 45.9 s |
| Structured extraction | 2,000 / 200 | $0.0030 | $0.0015 | 3.2 s |
More from Baidu
See also
Questions people ask
- Why does ERNIE-Light-DT-1.0 have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 22 Nov 2026 ERNIE-Light-DT-1.0 does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does ERNIE-Light-DT-1.0 cost per 1M tokens?
- As of 22 Nov 2026, ERNIE-Light-DT-1.0 costs $1.13 per 1M input tokens and $3.94 per 1M output tokens, $1.83 blended (three input tokens per output token).
Data as of 22 Nov 2026. Compare with another model.
Cite as: BenchLeader, “ERNIE-Light-DT-1.0: benchmarks, pricing, speed and rank”, data as of 22 Nov 2026, https://www.benchleader.com/models/ernie-light-dt-1-0-intl.