JoyAI-LLM-Flash: benchmark scores, price and ranking
JoyAI-LLM-Flash from jdopensource ranks #131 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.3), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- jdopensource
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #131 of 743 (score 51.3)
Across the 2 benchmarks where at least ten models are scored, JoyAI-LLM-Flash is in the top 10% on 0 and in the top half on 2.
JoyAI-LLM-Flash benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| MMLU-Pro | 81.0% | #32 of 136 | HuggingFace MMLU-Pro leaderboard | 2026-10-13 |
| GPQA Diamond | 74.4% | #132 of 275 | HuggingFace GPQA Diamond leaderboard | 2026-10-13 |
About JoyAI-LLM-Flash
JoyAI-LLM-Flash is an open-weight model that can run on your own hardware from jdopensource. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where JoyAI-LLM-Flash stands
On our aggregate score, JoyAI-LLM-Flash is #131 of 743 ranked models, in the top quarter. Its score is 51.3; the scale is centred on 50, so it sits 1.3 points above the typical model. That beats 82% of the ranked field.
JoyAI-LLM-Flash, benchmark by benchmark
MMLU-Pro puts JoyAI-LLM-Flash at 81.0%, #32 of 136. That beats 76% of the models tested, but 7.1 points short of Darwin-180B-RSI (88.1%). The results either side are MiniMax-M1-40k (81.1%) and Kimi K2 Instruct (81.0%). It covers 57-subject knowledge + reasoning. The board median is 55.3%, so JoyAI-LLM-Flash is 25.8 points above it. Source: HuggingFace MMLU-Pro leaderboard, captured 2026-10-13.
On GPQA Diamond, JoyAI-LLM-Flash reaches 74.4%. It ranks #132 of 275, ahead of 52% of the field, and 21.3 points behind GPT-6 Astra (max) at 95.8%. The results either side are GPT-5 mini (high) (75.0%) and A.X-K1 (74.0%). It covers expert-level science questions. The board median is 71.7%, so JoyAI-LLM-Flash is 2.7 points above it. Source: HuggingFace GPQA Diamond leaderboard, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: solid, ahead of 64% of the field on average across 2 benchmarks. Its best board here is MMLU-Pro (#32 of 136) and its weakest is GPQA Diamond (#132 of 275).
Reading these numbers
The 2 scores on this page come from 2 sources: HuggingFace GPQA Diamond leaderboard (1), HuggingFace MMLU-Pro leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #128 MiniMax-M1-40k (51.4)
- #129 Darwin-4B-David (51.3)
- #130 A.X-K1 (51.3)
- #132 Claude Opus 4.6 (120K, Medium) (51.3)
- #133 seed-oss-36b-instruct (51.3)
- #134 Darwin-9B-NEG (51.3)
Compare it on the live leaderboard → · How the aggregate score works