Category Score V3 leaderboard
LMSpeed Best Models for Knowledge
Compare AI models for broad and professional knowledge, factuality, retrieval, and open-book tasks using all eligible benchmark evidence in the active LMSpeed score run.
Methodology 3.0Methodology
Current answer
No model currently meets the formal ranking rules. The table has 7 Estimated models and 93 Provisional models. They are useful signals, but they are not formal ranks.
Available leaderboard data
- Models shown
- 100
- Formally ranked models
- 0
- Benchmark columns
- 10
- Dimensions with evidence
- 3/4
How to read the benchmark bars
Each bar compares models only within the same benchmark column. Bar lengths are relative to the models shown here; they are not Category Scores and cannot be compared across benchmark columns.
| Rank | Model | LMSpeed score | Broad knowledge | Professional knowledge | Factuality | Status | Evidence | Updated | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Omniscience Indexundefined models | BenchLM Knowledge scoreundefined models | Artificial Analysis Intelligence Indexundefined models | MMLU-Reduxundefined models | C-Evalundefined models | MMLUundefined models | SuperGPQAundefined models | HealthBench Hardundefined models | MedXpertQA (Text)undefined models | SimpleQAundefined models | ||||||
| Estimated models — unranked7 | |||||||||||||||
| — | Claude Opus 4.5Anthropic | 57.6±11.6 | — | — | — | 96.6 | 92.2 | — | 70.6 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.7 MaxQwen | 55.8±12.2 | — | — | — | 95.0 | — | — | 73.6 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.5 | 53.1±11.6 | — | — | — | 94.9 | 93.0 | — | 70.4 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.6 PlusQwen | 52±11.6 | — | — | — | 94.5 | 93.3 | — | 71.6 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.7 PlusQwen | 48.6±12.2 | — | — | — | 94.5 | — | — | 71.4 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.6 35B A3BQwen | 39.1±12.2 | — | — | — | — | 90.0 | — | 64.7 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.6 27BQwen | 37.3±11.6 | — | — | — | 93.5 | 91.4 | — | 66.0 | — | — | — | Estimated | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| Provisional models — unranked93 | |||||||||||||||
| — | Claude Sonnet 4.6Anthropic | 70.6±16.3 | — | — | — | — | — | — | 95.0 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 5Anthropic | 68.5±14.0 | 37.1 | 97.0 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Muse Spark 1.1Meta | 65.6±14.0 | 28.1 | 92.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 4.8Anthropic | 63.8±14.0 | 28.8 | 86.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | O1OpenAI | 62.5±17.4 | — | — | — | — | — | 91.8 | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.4 ProOpenAI | 62.2±16.1 | — | 88.0 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 4.7 MaxAnthropic | 61.8±14.0 | 27.3 | 81.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Kimi K3MoonshotAI | 61.2±14.0 | 19.7 | 83.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.5 ProOpenAI | 61±16.1 | — | 85.5 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Sonnet 5Anthropic | 60.9±14.0 | 16.5 | 84.6 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Fable 5Anthropic | 60.5±14.0 | 43.3 | 69.4 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | O3 ProOpenAI | 60.1±16.0 | — | — | 33.3 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.4OpenAI | 59.9±15.1 | — | — | — | — | — | — | — | 40.1 | 59.6 | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.5OpenAI | 59.3±14.0 | 20.5 | 77.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 4.1Anthropic | 59±16.0 | — | — | 28.8 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Grok 4.6SpaceXAI | 58.6±14.0 | 30.5 | 70.5 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek V4 Pro 0813DeepSeek | 58.4±18.0 | — | — | — | — | — | — | — | — | — | 57.9 | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Grok 4.5SpaceXAI | 58±14.0 | 25.3 | 71.1 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3.1 ProGoogle | 57.8±15.1 | — | — | — | — | — | — | — | 20.6 | 71.5 | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-5.2Z.ai | 57.8±14.0 | 4.4 | 81.2 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.2OpenAI | 57.7±14.0 | -0.9 | 83.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3.7 FlashGoogle | 57.5±14.0 | 26.5 | 69.0 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3.6 FlashGoogle | 57.5±14.0 | 22.1 | 71.2 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.6 SolOpenAI | 57.2±16.7 | — | — | — | — | — | — | — | 33.1 | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.6 TerraOpenAI | 57±16.7 | — | — | — | — | — | — | — | 32.7 | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-4.1OpenAI | 57±17.4 | — | — | — | — | — | 90.2 | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | O1 ProOpenAI | 56.5±16.0 | — | — | 19.1 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.6 LunaOpenAI | 56.5±16.7 | — | — | — | — | — | — | — | 32.0 | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Trinity Large ThinkingArcee AI | 56.4±16.0 | — | — | 18.7 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3 ProGoogle | 56.1±14.0 | 15.3 | 70.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Muse Spark 1.2Meta | 55.7±14.0 | 27.2 | 63.2 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | gpt-oss-120bOpenAI | 55.4±14.0 | — | 64.0 | 24.1 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-5.1Z.ai | 55.4±14.0 | 0.9 | 75.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.6 Max PreviewQwen | 55.1±16.3 | — | — | — | — | — | — | 73.9 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude 3 OpusAnthropic | 54.7±16.0 | — | — | 11.8 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek R1 Distill QwenDeepSeek | 54.4±16.0 | — | — | 11.0 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.3 CodexOpenAI | 54.4±16.0 | 10.9 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Sonnet 4.5Anthropic | 54.4±16.1 | — | 72.2 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 4.7Anthropic | 54.3±14.0 | 14.8 | 65.5 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 1.5 ProGoogle | 54.2±16.0 | — | — | 9.8 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | MiMo-V2.5-ProXiaomi | 54.1±14.0 | 3.3 | 70.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Opus 4.6Anthropic | 53.7±13.7 | — | — | — | — | — | — | 95.0 | 14.8 | 52.1 | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3.5 FlashGoogle | 53.7±14.0 | 21.2 | 60.4 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-4 TurboOpenAI | 53.6±16.0 | — | — | 7.7 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-4o MiniOpenAI | 53.4±16.0 | — | — | 6.7 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.1OpenAI | 53±16.0 | 5.4 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | MiMo-V2-Pro | 52.8±16.0 | 4.6 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Phi 4 Multimodal Instruct | 52.7±16.0 | — | — | 4.2 | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek V4 ProDeepSeek | 52.6±18.0 | — | — | — | — | — | — | — | — | — | 45.0 | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | InklingThinking Machines | 52.6±14.0 | 2.0 | 66.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.8 MaxQwen | 52.3±14.0 | 3.4 | 65.1 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | MiniMax M3MiniMax | 52.1±14.0 | 1.4 | 65.7 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | MiniMax M2.7MiniMax | 51.9±16.0 | 0.8 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Inkling SmallThinking Machines | 51.8±14.0 | -8.9 | 69.9 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3.5 Flash-LiteGoogle | 51.7±14.0 | 5.2 | 62.3 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Grok 4.3SpaceXAI | 51.5±14.0 | 18.0 | 55.4 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.2 CodexOpenAI | 51.1±16.0 | -2.2 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Command ACohere | 50.6±16.0 | -4.0 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Gemini 3 FlashGoogle | 50.6±16.0 | -4.3 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.1 Codex MaxOpenAI | 50±16.0 | -6.5 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.1 CodexOpenAI | 50±16.0 | -6.5 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5OpenAI | 49.5±16.0 | -8.7 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Claude Sonnet 4Anthropic | 49.4±16.0 | -9.0 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-4.1 MiniOpenAI | 49.3±17.4 | — | — | — | — | — | 87.5 | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Kimi K2.7 CodeMoonshotAI | 49.1±16.0 | -10.2 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-4oOpenAI | 49±16.0 | -10.5 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Kimi K2.6MoonshotAI | 48±14.0 | 5.3 | 51.3 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | O3 MiniOpenAI | 47.8±17.4 | — | — | — | — | — | 86.9 | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | O3OpenAI | 47.7±16.0 | -15.5 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek V4 Flash 0731DeepSeek | 47.5±18.0 | — | — | — | — | — | — | — | — | — | 34.1 | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-5 TurboZ.ai | 47.5±16.0 | -16.4 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Llama 3.1Meta | 47.3±16.0 | -17.1 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Kimi K2.5MoonshotAI | 47.1±16.3 | — | — | — | — | — | — | 69.2 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Hy3Tencent | 47±16.0 | -18.5 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-5V TurboZ.ai | 46.8±16.0 | -19.3 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | MiMo-V2-Omni | 46.6±16.0 | -20.1 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.4 MiniOpenAI | 46±14.0 | -18.9 | 57.6 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek R1DeepSeek | 44.7±16.0 | -27.4 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Kimi K2MoonshotAI | 44.5±16.0 | -28.3 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Grok 4.20SpaceXAI | 44.1±15.1 | — | — | — | — | — | — | — | 20.3 | 50.2 | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.5-122B-A10BQwen | 43.7±16.3 | — | — | — | — | — | — | 67.1 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Mistral Medium 3Mistral | 43.7±16.0 | -31.4 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-4.6Z.ai | 43.6±16.0 | -31.7 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Muse Glimmer 30BMeta | 43.3±16.0 | -32.8 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GPT-5.4 NanoOpenAI | 43.3±14.0 | -29.5 | 54.8 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | GLM-5Z.ai | 43.3±16.3 | — | — | — | — | — | — | 66.8 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Mistral Medium 3.5Mistral | 42.3±16.0 | -36.8 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Step 3.7 FlashStepFun | 42.2±16.0 | -37.3 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.8 27BQwen | 41.9±16.1 | — | 47.0 | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Mistral Large 3 | 41.6±16.0 | -39.6 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek V4 FlashDeepSeek | 41.4±18.0 | — | — | — | — | — | — | — | — | — | 23.1 | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | Qwen3.5-27BQwen | 41.4±16.3 | — | — | — | — | — | — | 65.6 | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
| — | DeepSeek V3 | 41.1±16.0 | -41.6 | — | — | — | — | — | — | — | — | — | Provisional | undefined/4 dimensions · undefined families | Aug 28, 2026 |
What this leaderboard measures
Which AI model is better suited to knowledge questions?
This leaderboard covers broad knowledge, professional knowledge, factuality, and use of open materials. It cannot guarantee that a model knows a recent event.
Four capability dimensions
The four dimensions come from the category blueprint. Available data may cover only some of them. A dimension without evidence is not presented as a verified capability.
Broad knowledge
6 benchmark columns currently provide evidence for this dimension.
- AA-Omniscience Index
- BenchLM Knowledge score
- Artificial Analysis Intelligence Index
- MMLU-Redux
- C-Eval
- MMLU
Professional knowledge
3 benchmark columns currently provide evidence for this dimension.
- SuperGPQA
- HealthBench Hard
- MedXpertQA (Text)
Factuality
1 benchmark columns currently provide evidence for this dimension.
- SimpleQA
Retrieval & open-book use
Available data has no eligible evidence for this dimension, so it does not affect this Category Score.
Knowledge tasks this page can help with
- General questions across common subjects with clear, useful answers.
- Professional research that requires domain terms and lower factual error rates.
- Retrieval-augmented questions that use external material instead of memory alone.
How to choose a model with this leaderboard
- Step 1
Check the rating status first
Only Rated models receive a rank. Estimated and Provisional models do not have a formal position.
- Step 2
Review uncertainty and evidence
When scores are close, do not rely on rank alone. Check uncertainty, dimension coverage, and benchmark count.
- Step 3
Test the real task last
A leaderboard cannot replace your own test. Check quality, speed, price, context, and provider limits together.
Use search or reliable sources for time-sensitive questions. Important conclusions still need source checks.
Rating status guide
Rated
Rated means the evidence and overlap rules are met. The model can receive a formal rank.
Estimated
Estimated means there is useful evidence, but it is not enough for a formal rank.
Provisional
Provisional means evidence is limited or dimension and benchmark-family coverage is below the estimated threshold. Use the result only as an early signal.
Benchmarks and evidence sources
Evidence source names and benchmark groups come from the currently available score data. One source may contribute several benchmarks.
BenchLM
AA-Omniscience Index, Artificial Analysis Intelligence Index, BenchLM Knowledge score, C-Eval, HealthBench Hard, MedXpertQA (Text), MMLU, MMLU-Redux, SimpleQA, and SuperGPQA
How the knowledge model ranking is built
LMSpeed combines eligible third-party benchmarks inside four fixed capability dimensions. Rated models meet the evidence and overlap requirements for a formal rank; Estimated and Provisional models remain visible without receiving a rank.
Read the Category Score methodologyLeaderboard limits
Category Scores use the third-party benchmarks currently included by LMSpeed. Tests can use different data, prompts, and scoring rules. The result is not permanent and cannot represent every real task. Test important choices with your own data and workflow.
Frequently asked questions
Which visible model has the highest formal rank now?
There is no formal number one now. The page has 7 Estimated models and 93 Provisional models. They do not have a formal rank and should not be called the winner.
Can I compare scores across different categories?
No. Each category uses different capability dimensions and evidence. A Category Score is comparable only inside the same leaderboard. Review the matching category for each task.
Are Estimated and Provisional models still useful?
They can help you find candidates, but their evidence is not complete enough for a formal rank. Review coverage and uncertainty, then test the model on a real task.
How often does the leaderboard update?
The leaderboard updates after a new completed score run is published. The current run date and methodology version appear above. LMSpeed does not promise a fixed daily or weekly schedule.
Is the number one model always best for me?
No. Your result also depends on speed, price, context length, tool support, region, and provider limits. Use the leaderboard to narrow the field, then run your own test.
Does a high knowledge score prevent factual errors?
No. A high score only shows stronger results on the current knowledge benchmarks. The model can still return old or incorrect information. Check dates and primary sources for important facts.