Benchmark Almanac

ERNIE 5.1

ERNIE 5.1 places in the top three on AIME 2026.

Baidu Released May 9th, 2026 Family ERNIE 5 The lab's model card Compare with others
13
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Baidu May 2026

ERNIE 5.1

Closed weights Flagship

149.7 #98 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • ClawProBench 68.6% #5 /49
  • MMLU-Pro 84.3% #41 /167
  • DeepSearchQA 77.3% #17 /23

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
LMArena (Elo) 1,467 #42 of 335 Official leaderboard
MMLU-Pro 84.3% #41 of 167 Lab model card
AdvancedIF 72.3% #4 of 6 Lab model card
Extended NYT Connections 23.4% #87 of 103 Official leaderboard
Antidote 947 #32 of 36 Official leaderboard

Math and science

BenchmarkScoreRankSource
AIME 2026 99.6% #2 of 38 Lab model card
GPQA Diamond 91% #25 of 302 Lab model card

Agents and tools

BenchmarkScoreRankSource
ClawProBench 68.6% #5 of 49 Official leaderboard
tau3-bench 67.9% #8 of 14 Lab model card
LMArena Search Arena 1,192 #23 of 37 Official leaderboard
DeepSearchQA 77.3% #17 of 23 Lab model card
PACT 1,485 #22 of 26 Official leaderboard

Professional work

BenchmarkScoreRankSource
SpreadsheetBench Verified 72.5% #2 of 2 Lab model card

Its lab's numbers put it at 149.7, number 98 of 404

The Self-Reported Index fits one score to the 5 capability results Baidu reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 144.0 to 155.4. How we compute it.

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap What differs
LMArena Search Arena 1,223 Arena Search leaderboard, 1,223, 4th globally on May 9 1,192 Leaderboard +31 Baidu quotes the May 9 Arena Search rating, while the comparison uses a later leaderboard snapshot.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.