reasoning benchmark
TriviaQA Leaderboard
TriviaQA is a large-scale reading comprehension dataset with over 650K question-answer-evidence triples, including 95K question-answer pairs and independently gathered evidence documents.
Updated Sep 5, 2026
Models18
Model coverage18
MetricScore
EvidenceB
TriviaQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score85.10% | Percentile100.00% | Participants18 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score83.70% | Percentile94.12% | Participants18 | EvidenceC | Evaluated |
| Rank03 | ModelXI | Score81.30% | Percentile88.24% | Participants18 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score80.50% | Percentile82.35% | Participants18 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score80.50% | Percentile76.47% | Participants18 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score80.32% | Percentile70.59% | Participants18 | EvidenceC | Evaluated |
| Rank07 | ModelIB | Score78.18% | Percentile64.71% | Participants18 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score76.60% | Percentile58.82% | Participants18 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score74.90% | Percentile52.94% | Participants18 | EvidenceC | Evaluated |
| Rank10 | ModelMA | Score74.90% | Percentile47.06% | Participants18 | EvidenceC | Evaluated |
| Rank11 | ModelMA | Score73.80% | Percentile41.18% | Participants18 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score70.20% | Percentile35.29% | Participants18 | EvidenceC | Evaluated |
| Rank13 | ModelGO | Score70.20% | Percentile29.41% | Participants18 | EvidenceC | Evaluated |
| Rank14 | ModelMA | Score68.10% | Percentile23.53% | Participants18 | EvidenceC | Evaluated |
| Rank15 | ModelMA | Score65.50% | Percentile17.65% | Participants18 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score60.80% | Percentile11.76% | Participants18 | EvidenceC | Evaluated |
| Rank17 | ModelGO | Score60.80% | Percentile5.88% | Participants18 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score59.20% | Percentile0.00% | Participants18 | EvidenceC | Evaluated |
TriviaQA Highlights
The leading models and scores on this benchmark.
TriviaQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for TriviaQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is TriviaQA?
What TriviaQA measures and how its scores work.
TriviaQA is a reasoning benchmark based on complex, compositional questions and evidence documents for answering them.
It reports a Score expressed as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TriviaQA
- Modality
- text
- Primary category
- reasoning
- 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 TriviaQA.
Which model scores highest on TriviaQA?
Kimi K2 Base is currently ranked first with 85.10%.
What are the top three models on TriviaQA?
The current leaders are Kimi K2 Base (85.10%), Gemma 2 27B (83.70%), and MiMo-V2.5-Pro (81.30%).
Which TriviaQA model has the lowest official input price?
Ministral 3 (14B Base 2512) has the lowest matched official input price at $0.10 input / $0.10 output per 1M tokens.
Which models are fastest among TriviaQA results?
The fastest matched records are Mistral Small 3.1 24B Base (137.10 tok/s via Mistral AI), Mistral Small 3.1 24B Instruct (137.10 tok/s via Mistral AI), and Mistral NeMo Instruct (42.00 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.