Open LLM Leaderboard v2
Indexed results from Open LLM Leaderboard v2 · Archive. Each ranking retains its own metric and evaluation conditions.
Open LLM v2 GPQA · Normalized
openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Normalized score · percent
- Steelskull/L3.3-MS-Nevoria-70bsteelskull29.418%
- Steelskull/L3.3-Nevoria-R1-70bsteelskull29.195%
- Tarek07/Progenitor-V1.1-LLaMa-70Btarek0727.74%
- rootxhacker/Apollo-70Brootxhacker27.629%
- Sao10K/70B-L3.3-Cirrus-x1sao10k26.622%
- Triangle104/Set-70btriangle10426.174%
- Daemontatox/Llama3.3-70B-CogniLinkdaemontatox26.063%
- Tarek07/Thalassic-Alpha-LLaMa-70Btarek0725.839%
- mistralai/Mistral-Large-Instruct-2411mistralai24.944%
- OpenBuddy/openbuddy-llama3.3-70b-v24.1-131kopenbuddy24.609%
- pankajmathur/orca_mini_v8_1_70bpankajmathur24.385%
- JungZoona/T3Q-Qwen2.5-14B-Instruct-1M-e3jungzoona22.26%
Models
LoadingBenchmarks
Explore every benchmark
LoadingThese charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.