WMT 2014 Leaderboard

Workshop on Machine Translation 2014 — multilingual translation quality benchmark.

Data from LayerLens

As of November 21, 2026, the top-scoring model on WMT 2014 is Llama 4 Maverick at 38.0%, followed by GPT-4.1 at 37.6% and GPT-4o at 37.5%. 7 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

7

Best Score

38.0

Average

35.6

Std Dev

4.3

Categories
Multilingual
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
WMT 2014
Actions
$0.200
$0.600
38.0
$2.000
$8.000
37.6
$2.500
$10.000
37.5
$0.100
$0.300
37.1
$0.800
$3.200
36.9
$0.014
$0.028
36.6
$0.030
$0.050
25.2

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About WMT 2014

Workshop on Machine Translation 2014 — multilingual translation quality benchmark.

This leaderboard shows all models with WMT 2014 benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

Workshop on Machine Translation 2014 — multilingual translation quality benchmark.
As of November 21, 2026, Llama 4 Maverick leads the WMT 2014 leaderboard with a score of 38.0. Rankings change as new models are released and evaluated.
Currently 7 models have been evaluated on WMT 2014, with an average score of 35.6 and standard deviation of 4.3.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.