language benchmark
WMT23 Leaderboard
WMT23 is a machine translation benchmark covering 8 language pairs and 14 translation directions across general, biomedical, literary, and low-resource translation tasks.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
WMT23 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score75.10% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score74.10% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelGO | Score72.60% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score71.70% | Percentile0.00% | Participants4 | EvidenceB | Evaluated |
WMT23 Highlights
The leading models and scores on this benchmark.
WMT23 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for WMT23
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is WMT23?
What WMT23 measures and how its scores work.
WMT23 is the benchmark from the Eighth Conference on Machine Translation, featuring shared tasks for quality estimation, metrics evaluation, sign language translation, and discourse-level literary translation.
It evaluates machine translation systems across the listed translation tasks, including assessment through professional human evaluation.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- WMT23
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about WMT23.
Which model scores highest on WMT23?
Gemini 1.5 Pro is currently ranked first with 75.10%.
What are the top three models on WMT23?
The current leaders are Gemini 1.5 Pro (75.10%), Gemini 1.5 Flash (74.10%), and Gemini 1.5 Flash 8B (72.60%).
Which WMT23 model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among WMT23 results?
The fastest matched records are Gemini 1.5 Flash (150.00 tok/s via Google), Gemini 1.5 Flash 8B (150.00 tok/s via Google), and Gemini 1.0 Pro (120.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.