Created bymario-alka.dePowered bygodcore.denoob2claw.detricoma.de
🏆
Rankings

LLM Leaderboard

Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.

⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
Reset
Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
1.171,75 tok/s TG
Prefill 2.132 · TTFT 45.396 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS
2Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
589,46 tok/s TG
Prefill 2.120 · TTFT 21.049 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS
3Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
242,41 tok/s TG
Prefill 4.265 · TTFT 17.947 ms
10×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS
4Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
139,55 tok/s TG
Prefill 3.687 · TTFT 3.821 ms
5×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS
5Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,24 tok/s TG
Prefill 1.458 · TTFT 1.399 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS
6Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
115,48 tok/s TG
Prefill 1.754 · TTFT 1.124 ms
1×NVIDIA RTX A6000AMD Ryzen Threadripper PRO 3945WX 12-CoresstrataIQ2_XS