reasoning benchmark
TriviaQA Leaderboard
A large-scale reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents (six per question on average) that provide high quality distant supervision for answering the questions. The dataset features relatively complex, compositional questions with considerable syntactic and lexical variability, requiring cross-sentence reasoning to find answers.
Updated Aug 17, 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 | Score85.1% | Percentile100.0% | Participants18 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score83.7% | Percentile94.1% | Participants18 | EvidenceC | Evaluated |
| Rank03 | ModelXI | Score81.3% | Percentile88.2% | Participants18 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score80.5% | Percentile82.3% | Participants18 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score80.5% | Percentile76.5% | Participants18 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score80.3% | Percentile70.6% | Participants18 | EvidenceC | Evaluated |
| Rank07 | ModelIB | Score78.2% | Percentile64.7% | Participants18 | EvidenceC | Evaluated |
| Rank08 | ModelGO | Score76.6% | Percentile58.8% | Participants18 | EvidenceC | Evaluated |
| Rank09 | ModelMA | Score74.9% | Percentile52.9% | Participants18 | EvidenceC | Evaluated |
| Rank10 | ModelMA | Score74.9% | Percentile47.1% | Participants18 | EvidenceC | Evaluated |
| Rank11 | ModelMA | Score73.8% | Percentile41.2% | Participants18 | EvidenceC | Evaluated |
| Rank12 | ModelGO | Score70.2% | Percentile35.3% | Participants18 | EvidenceC | Evaluated |
| Rank13 | ModelGO | Score70.2% | Percentile29.4% | Participants18 | EvidenceC | Evaluated |
| Rank14 | ModelMA | Score68.1% | Percentile23.5% | Participants18 | EvidenceC | Evaluated |
| Rank15 | ModelMA | Score65.5% | Percentile17.6% | Participants18 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Score60.8% | Percentile11.8% | Participants18 | EvidenceC | Evaluated |
| Rank17 | ModelGO | Score60.8% | Percentile5.9% | Participants18 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score59.2% | Percentile0.0% | 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.
Ranking basisThis triviaqa AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MAKimi K2 BaseMoonshot AI
- Score
- 85.1%
- Price
- $0.60 input / $2.5 output per 1M tokens
- Speed
- Up to 45 tok/s via Novita
Strengths
- Ranks #1 of 18 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures TriviaQA, not total model capability
- 02GOGemma 2 27BGoogle
- Score
- 83.7%
Strengths
- Ranks #2 of 18 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures TriviaQA, not total model capability
- 03XIMiMo-V2.5-ProXiaomi
- Score
- 81.3%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 69 tok/s via Novita
Strengths
- Ranks #3 of 18 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures TriviaQA, not total model capability
- 04MAMistral Small 3.1 24B BaseMistral AI
- Score
- 80.5%
- Speed
- Up to 137 tok/s via Mistral AI
Strengths
- Ranks #4 of 18 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures TriviaQA, not total model capability
- 05MAMistral Small 3.1 24B InstructMistral AI
- Score
- 80.5%
- Speed
- Up to 137 tok/s via Mistral AI
Strengths
- Ranks #5 of 18 compared models
- 76th percentile on this benchmark
- C evidence result
Considerations
- This result measures TriviaQA, not total model capability
Selection summary
Best AI Models for TriviaQA
Kimi K2 Base currently leads TriviaQA with 85.1%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is TriviaQA?
What TriviaQA measures and how its scores work.
A large-scale reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents (six per question on average) that provide high quality distant supervision for answering the questions. The dataset features relatively complex, compositional questions with considerable syntactic and lexical variability, requiring cross-sentence reasoning to find answers.
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
- Yes
- Evaluation key
- triviaqa|llm-stats-current
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 85.1%.
What does TriviaQA measure?
A large-scale reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents (six per question on average) that provide high quality distant supervision for answering the questions. The dataset features relatively complex, compositional questions with considerable syntactic and lexical variability, requiring cross-sentence reasoning to find answers.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
18 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.