List your company

Throughput Measurement on GPQA Diamond

1,440.8Throughput (tokens/s)FLARE-2B
-12.704364.6487421,119.352Jun 1, 2026

Evaluation results

MethodLinks
FLARE-2BConcurrency level (C)=82026.061,440.8
FLARE-4BConcurrency level (C)=82026.06990.4
FLARE-2BConcurrency level (C)=42026.06949
FLARE-9BConcurrency level (C)=82026.06786.5
FLARE-4BConcurrency level (C)=42026.06649.3
FLARE-9BConcurrency level (C)=42026.06499
SDAR-1.7BConcurrency level (C)=82026.06461.5
SDAR-4BConcurrency level (C)=82026.06441.7
LLaDA-2.1-miniConcurrency level (C)=82026.06401.2
SDAR-1.7BConcurrency level (C)=42026.06383.1
SDAR-8BConcurrency level (C)=82026.06379.3
LLaDA-2.0-miniConcurrency level (C)=82026.06373.2
FLARE-2BConcurrency level (C)=12026.06330.7
SDAR-4BConcurrency level (C)=42026.06313.6
LLaDA-2.1-miniConcurrency level (C)=42026.06283.9
LLaDA-2.0-miniConcurrency level (C)=42026.06264.2
FLARE-4BConcurrency level (C)=12026.06237.4
SDAR-8BConcurrency level (C)=42026.06229.6
LLaDA-2.1-miniConcurrency level (C)=12026.06226.9
SDAR-30B-A3BConcurrency level (C)=82026.06210.2
LLaDA-2.0-miniConcurrency level (C)=12026.06182.6
FLARE-9BConcurrency level (C)=12026.06170.8
SDAR-1.7BConcurrency level (C)=12026.06130.4
SDAR-30B-A3BConcurrency level (C)=42026.06120.6
SDAR-4BConcurrency level (C)=12026.0695.7
SDAR-8BConcurrency level (C)=12026.0672.2
SDAR-30B-A3BConcurrency level (C)=12026.0643.2