Leaderboard
Discover the top-performing models based on total token usage.
| Rank | Model | Total Tokens |
|---|---|---|
#1 🥇 |  Qwen/Qwen3-30B-A3B-Instruct-2507 Qwen/Qwen3-30B-A3B-Instruct-2507 | 1.5B |
#2 🥈 |  moonshotai/Kimi-K2-Thinking-edebened moonshotai/Kimi-K2-Thinking-edebened | 271.1M |
#3 🥉 |  openai/gpt-oss-120b openai/gpt-oss-120b | 210.4M |
#4 |  Snowflake/snowflake-arctic-embed-l-v2.0 Snowflake/snowflake-arctic-embed-l-v2.0 | 135.1M |
#5 | Qwen/Qwen3-Next-80B-A3B-Instruct Qwen/Qwen3-Next-80B-A3B-Instruct | 125.7M |
#6 | moonshotai/Kimi-K2-Instruct-do-not-use-edebened moonshotai/Kimi-K2-Instruct-do-not-use-edebened | 37.3M |
#7 | moonshotai/Kimi-K2-Thinking-do-not-use-edebened moonshotai/Kimi-K2-Thinking-do-not-use-edebened | 32.6M |
#8 |  deepseek-ai/DeepSeek-V3.1 deepseek-ai/DeepSeek-V3.1 | 32.2M |
#9 |  swiss-ai/Apertus-8B-Instruct-2509 swiss-ai/Apertus-8B-Instruct-2509 | 31.7M |
#10 | swiss-ai/Apertus-8B-Instruct-2509-sinliu swiss-ai/Apertus-8B-Instruct-2509-sinliu | 20.8M |
#11 | Qwen/Qwen2.5-Coder-14B-Instruct Qwen/Qwen2.5-Coder-14B-Instruct | 20.4M |
#12 | swiss-ai/Apertus-70B-Instruct-2509 swiss-ai/Apertus-70B-Instruct-2509 | 19.7M |
#13 | Qwen/Qwen3-32B Qwen/Qwen3-32B | 13.7M |
#14 |  mistralai/Mistral-7B-v0.1 mistralai/Mistral-7B-v0.1 | 5.0M |
#15 | moonshotai/Kimi-K2-Instruct moonshotai/Kimi-K2-Instruct | 1.0M |
#16 | moonshotai/Kimi-K2-Thinking moonshotai/Kimi-K2-Thinking | 175.9K |
#17 | mistralai/Mistral-7B-Instruct-v0.3 mistralai/Mistral-7B-Instruct-v0.3 | 153.0K |
#18 | Qwen/Qwen3-8B Qwen/Qwen3-8B | 97.6K |
#19 |  zai-org/GLM-4.6 zai-org/GLM-4.6 | 34.8K |
#20 | TildeAI/TildeOpen-30b TildeAI/TildeOpen-30b | 22.3K |
#21 | swiss-ai/Apertus-8B-Instruct-2509-rosmith swiss-ai/Apertus-8B-Instruct-2509-rosmith | 18.7K |
#22 |  meta-llama/Llama-3.3-70B-Instruct meta-llama/Llama-3.3-70B-Instruct | 11.4K |
#23 | Qwen/Qwen3-4B-Instruct-2507 Qwen/Qwen3-4B-Instruct-2507 | 155 |