Skip to main content
Meo

Baidu: ERNIE 4.5 VL 424B A47B

Baidu: ERNIE 4.5 VL 424B A47B is baidu's model. On the un-leaked meo benchmark it ranks #41 of 82 with 63.2% accuracy and an Effective Value (𝕍) of 0.0006 β€” earning a correct answer for about $0.0087 in 192s each.

as of 2026-10-18

meo rank
#41
of 82
Accuracy
63.2%
overall
𝕍 index (top=100)
0.015
raw 𝕍 0.0006 Β· N=10
$ / correct
$0.0087
192s each

Per-domain accuracy

159 correct of 250 questions asked across 11 domains Β· answer rate 100% Β· macro accuracy 62.3%. Headline accuracy is micro-averaged per meo’s methodology; per-domain question counts (correct/asked) are shown so you can judge significance.

Theory of mind
100%3/3
Regex automaton
88%14/16
Base-rate bias
80%33/41
Tape machine
80%12/15
Watson-Glaser
75%3/4
Logic / math / CS
68%23/34
Framework bias
67%2/3
CSP (unsatisfiable)
63%10/16
Perceptual illusions
58%59/102
State tracking
0%0/1
Long arithmetic
0%0/15

Efficiency

Cost per correct
$0.0087
Seconds per correct
192
Tokens per correct
6,546
Correct answers
159 / 250
Total benchmark cost
$1.38
Avg tokens / item
4,163

Model details

Released
2025-06-30
Weights
Open
Context
131K
Max output
16K
Knowledge cutoff
2025-03-31
Price in
$0.42/M
Price out
$1.25/M
Modality
text+image->text
View on OpenRouter β†—Hugging Face β†—

Sources: openrouter Β· meo

FAQ

How accurate is Baidu: ERNIE 4.5 VL 424B A47B ?

Baidu: ERNIE 4.5 VL 424B A47B scores 63.2% overall on the meo benchmark (rank #41 of 82), an un-leaked private holdout graded objective-first.

What is Baidu: ERNIE 4.5 VL 424B A47B 's Effective Value?

Its Effective Value (𝕍) is 0.0006 at N=10, Ο‰=1, Ξ΄=1.5 β€” a fused metric of accuracy, speed, cost, and error-cascade. 𝕍 rankings shift with task depth.

How much does Baidu: ERNIE 4.5 VL 424B A47B cost per correct answer?

About $0.0087 per correct answer (6,546 tokens, 192 seconds each) at benchmark-time pricing via OpenRouter.

Is Baidu: ERNIE 4.5 VL 424B A47B open weights?

Yes β€” Baidu: ERNIE 4.5 VL 424B A47B is released with open weights.

Benchmark updates affecting this model

  • 2026-06-09majorlogic_math_cs ground truth was broken β€” culled and rebuilt with solver-verified items

    A 5-lab frontier jury revealed that 29 of 37 LLM-authored logic_math_cs items had broken ground truth: on most, five independent frontier models unanimously concluded the clue sets were contradictory while the stored answer claimed a number, and on eight, all five agreed on the SAME different number (author arithmetic errors). Models were being marked wrong for being right. The 29 were retired (full audit published in the repo) and the domain rebuilt with generator-as-oracle items: an embedded constraint solver PROVES each puzzle has exactly one solution (or provably none), verified by an independent exhaustive enumerator. A 3-round difficulty study found frontier models saturate consistent human-scale logic puzzles, so items use anonymous global constraints and carry a measured difficulty gradient.

  • 2026-06-08majorCorrected base_bias grading (LLM-equivalence judge fix)

    The LLM-equivalence grader uses a reasoning model whose verdict token budget was too small, so its YES/NO answer was emitted as empty and silently counted as a failure. This understated the base_bias domain to ~7% for every model when the true accuracy is ~85-90%. We raised the judge budget, excluded its reasoning tokens from the verdict, switched to verbosity-robust conclusion matching, and re-graded the whole board.

Full benchmark changelog β†’

Embed this ranking

Show Baidu: ERNIE 4.5 VL 424B A47B ’s meo rank on your site β€” the badge links back here.

Related: all Baidu models Β· Theory of mind domain Β· best Effective Value Β· biggest movers Β· methodology Β· full leaderboard.