List your company

Text Generation on NoveltyBench

10Diversityλ-PR
1.13923.43965.748.0404Feb 15, 2026Feb 27, 2026Mar 11, 2026Mar 24, 2026Apr 5, 2026Apr 17, 2026Apr 30, 2026

Evaluation results

MethodLinks
λ-PRSFT Dataset=UF, Backbone=MISTRAL-12B2026.04101.1
λ-PRSFT Dataset=UF, Backbone=LLAMA-3.1-8B2026.04101.1
λ-PRSFT Dataset=UF, Backbone=OLMO-2-13B2026.049.91.1
λ-PRSFT Dataset=UF, Backbone=PYTHIA-12B2026.049.91
λ-PRSFT Dataset=UF, Backbone=QWEN-3-8B2026.049.91.1
λ-PRSFT Dataset=UF, Backbone=PHI-4-14B2026.049.91.1
λ-PRSFT Dataset=ALPACA, Backbone=PHI-4-14B2026.049.61.2
λ-PRSFT Dataset=ALPACA, Backbone=MISTRAL-12B2026.049.51.3
λ-PRSFT Dataset=ALPACA, Backbone=LLAMA-3.1-8B2026.049.51.3
GEMSFT Dataset=UF, Backbone=PYTHIA-12B2026.049.51.4
TOFUSFT Dataset=UF, Backbone=PYTHIA-12B2026.049.51.4
λ-PRSFT Dataset=ALPACA, Backbone=OLMO-2-13B2026.049.41.3
λ-PRSFT Dataset=ALPACA, Backbone=PYTHIA-12B2026.049.31.1
FLSFT Dataset=UF, Backbone=PYTHIA-12B2026.049.31.6
TOFUSFT Dataset=UF, Backbone=LLAMA-3.1-8B2026.049.32.6
λ-PRSFT Dataset=ALPACA, Backbone=QWEN-3-8B2026.049.11.2
GEMSFT Dataset=UF, Backbone=OLMO-2-13B2026.049.12.8
GEMSFT Dataset=UF, Backbone=LLAMA-3.1-8B2026.049.12.6
TOFUSFT Dataset=UF, Backbone=MISTRAL-12B2026.049.12.6
TOFUSFT Dataset=UF, Backbone=OLMO-2-13B2026.049.12.9
GEMSFT Dataset=UF, Backbone=MISTRAL-12B2026.0492.8
FLSFT Dataset=UF, Backbone=LLAMA-3.1-8B2026.048.92.8
TOFUSFT Dataset=UF, Backbone=PHI-4-14B2026.048.92
TOFUSFT Dataset=ALPACA, Backbone=PYTHIA-12B2026.048.83
FLSFT Dataset=UF, Backbone=OLMO-2-13B2026.048.83
GEMSFT Dataset=UF, Backbone=QWEN-3-8B2026.048.82.8
TOFUSFT Dataset=UF, Backbone=QWEN-3-8B2026.048.82.8
GEMSFT Dataset=ALPACA, Backbone=PYTHIA-12B2026.048.73
GEMSFT Dataset=UF, Backbone=PHI-4-14B2026.048.62
FLSFT Dataset=ALPACA, Backbone=PYTHIA-12B2026.048.53.2
CESFT Dataset=UF, Backbone=PYTHIA-12B2026.048.51.7
FLSFT Dataset=UF, Backbone=MISTRAL-12B2026.048.52.9
FLSFT Dataset=UF, Backbone=PHI-4-14B2026.048.42.3
TOFUSFT Dataset=ALPACA, Backbone=OLMO-2-13B2026.048.34.4
TOFUSFT Dataset=ALPACA, Backbone=LLAMA-3.1-8B2026.048.34.3
TOFUSFT Dataset=ALPACA, Backbone=MISTRAL-12B2026.048.24.4
FLSFT Dataset=UF, Backbone=QWEN-3-8B2026.048.22.9
GEMSFT Dataset=ALPACA, Backbone=OLMO-2-13B2026.048.14.6
GEMSFT Dataset=ALPACA, Backbone=LLAMA-3.1-8B2026.048.14.7
GEMSFT Dataset=ALPACA, Backbone=MISTRAL-12B2026.0484.5
TOFUSFT Dataset=ALPACA, Backbone=QWEN-3-8B2026.047.94.2
CESFT Dataset=ALPACA, Backbone=PYTHIA-12B2026.047.73.2
FLSFT Dataset=ALPACA, Backbone=OLMO-2-13B2026.047.74.5
FLSFT Dataset=ALPACA, Backbone=LLAMA-3.1-8B2026.047.74.2
GEMSFT Dataset=ALPACA, Backbone=QWEN-3-8B2026.047.64.3
CESFT Dataset=UF, Backbone=LLAMA-3.1-8B2026.047.62.9
TOFUSFT Dataset=ALPACA, Backbone=PHI-4-14B2026.047.52
FLSFT Dataset=ALPACA, Backbone=MISTRAL-12B2026.047.44.3
FLSFT Dataset=ALPACA, Backbone=QWEN-3-8B2026.047.44.3
CESFT Dataset=UF, Backbone=MISTRAL-12B2026.047.33.2
CESFT Dataset=UF, Backbone=OLMO-2-13B2026.047.33
GEMSFT Dataset=ALPACA, Backbone=PHI-4-14B2026.047.21.8
FLSFT Dataset=ALPACA, Backbone=PHI-4-14B2026.047.12
CESFT Dataset=UF, Backbone=QWEN-3-8B2026.0472.9
CESFT Dataset=UF, Backbone=PHI-4-14B2026.046.92.2
CESFT Dataset=ALPACA, Backbone=MISTRAL-12B2026.046.64.3
CESFT Dataset=ALPACA, Backbone=OLMO-2-13B2026.046.54.2
CESFT Dataset=ALPACA, Backbone=LLAMA-3.1-8B2026.046.54.2
CESFT Dataset=ALPACA, Backbone=QWEN-3-8B2026.046.54.2
CESFT Dataset=ALPACA, Backbone=PHI-4-14B2026.045.81.7
STATe of ThoughtsTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.025.394.01
STATe of ThoughtsTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.025.023.83
STATe of ThoughtsTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.024.873.77
CoT w/ Action SpaceTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.023.743.49
ToT w/ Action SpaceTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.023.613.61
CoT w/ Action SpaceTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.023.363.28
ToT w/ Action SpaceTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.023.253.36
ToTTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.023.163.32
ToT w/ Action SpaceTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.023.163.29
CoT w/ Action SpaceTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.023.073.15
ToTTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.022.813.07
CoTTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.022.83.07
ToTTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.022.512.87
CoTTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.022.442.85
I/O w/ Action SpaceTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.022.442.71
CoTTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.022.152.65
I/OTemperature (T)=1.0, Backbone=Qwen3-30B-A3B-Instruct2026.022.012.64
I/O w/ Action SpaceTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.022.012.41
I/O w/ Action SpaceTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.021.742.23
I/OTemperature (T)=0.7, Backbone=Qwen3-30B-A3B-Instruct2026.021.672.45
I/OTemperature (T)=0.5, Backbone=Qwen3-30B-A3B-Instruct2026.021.482.28