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
Models
7
Best Score
38.0
Average
35.6
Std Dev
4.3
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.
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.
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.