List your company

Decoding Throughput on HumanEval

1,763.9Throughput (tok/s)FLARE-2B
-29.164436.343901.851,367.357Jun 1, 2026

Evaluation results

MethodLinks
FLARE-2BConcurrency level (C)=82026.061,763.9—————
LLaDA-2.1-miniConcurrency level (C)=82026.061,646.5—————
LLaDA-2.1-miniConcurrency level (C)=42026.061,471.4—————
FLARE-4BConcurrency level (C)=82026.061,178.9—————
FLARE-2BConcurrency level (C)=42026.061,113.3—————
FLARE-9BConcurrency level (C)=82026.061,007.1—————
FLARE-4BConcurrency level (C)=42026.06812.2—————
FLARE-9BConcurrency level (C)=42026.06642.8—————
LLaDA-2.0-miniConcurrency level (C)=82026.06626.1—————
LLaDA-2.0-miniConcurrency level (C)=42026.06496.7—————
LLaDA-2.1-miniConcurrency level (C)=12026.06472.4—————
SDAR-1.7BConcurrency level (C)=82026.06427—————
SDAR-4BConcurrency level (C)=82026.06398.3—————
FLARE-2BConcurrency level (C)=12026.06373.5—————
SDAR-8BConcurrency level (C)=82026.06372.1—————
SDAR-1.7BConcurrency level (C)=42026.06364.7—————
SDAR-4BConcurrency level (C)=42026.06326.1—————
SDAR-8BConcurrency level (C)=42026.06276.8—————
FLARE-4BConcurrency level (C)=12026.06268.2—————
LLaDA-2.0-miniConcurrency level (C)=12026.06234.2—————
SDAR-30B-A3BConcurrency level (C)=82026.06214.1—————
FLARE-9BConcurrency level (C)=12026.06203.2—————
SDAR-1.7BConcurrency level (C)=12026.06135.6—————
SDAR-30B-A3BConcurrency level (C)=42026.06122.3—————
SDAR-4BConcurrency level (C)=12026.06105.1—————
SDAR-8BConcurrency level (C)=12026.0683.8—————
SDAR-30B-A3BConcurrency level (C)=12026.0639.8—————
AutoregressiveModel=Llama-3.1-Instruct 70B/1B2026.03—54.7————
AutoregressiveModel=Qwen-3 32B/0.6B2026.03—88.8————
Speculative DecodingModel=Llama-3.1-Instruct 70B/1B2026.03——176———
Speculative DecodingModel=Qwen-3 32B/0.6B2026.03——146———
SSDModel=Llama-3.1-Instruct 70B/1B2026.03———2831.65.17
SSDModel=Qwen-3 32B/0.6B2026.03———2221.522.5