Decision models enable fast, confidence-aware decisions by scoring candidate answers in a single forward pass, without generating text or intermediate reasoning. Yet reasoning can substantially improve decision quality, raising the question of whether its benefits can be retained without the cost of generating it. We investigate this question with GLiDE, a family of decision models spanning 0.4B to 27B parameters. Building on Qwen hybrid language models, GLiDE enables bidirectional interactions between the context, question, and candidate answers by removing causal masking from full-attention layers. To transfer reasoning capabilities into single-pass inference, we combine soft-target distillation from multiple teachers, including a reasoning model, with progressive post-training on diverse decision tasks. We further explore parameter-free recurrent depth to increase inference-time computation without generating tokens. Across five model sizes, GLiDE lies on the performance--parameter Pareto frontier of the Hugging Face \DI{}, with each model outperforming evaluated alternatives of equal or smaller size. \dmtwo{} (27B) achieves a hidden-set score of 71.52, with an expected calibration error of 2.0% and a median latency of 92.9,ms on a single GPU. Further checkpoint averaging and parameter-free recurrent depth yield GLiDE~27B, which reaches 73.37 with an expected calibration error of 2.1%.
Figures & tables
Figure 1: GLiDE V1.2 remains within 0.6 points of the highest score across three versions of the Artificial Analysis Decision Index. The model was not retrained between versions. Numbers are the scores the leaderboard showed on the date above each panel, in whole points. In unrounded scores GLiDE V1.2 is 0.2, 0.6 and 0.1 points below the highest model (Table 5 ). Scored by Artificial Analysis itself; part of its test data is private.
Figure 2: GLiDE V1.2 architecture. Each decision is encoded as a single sequence containing the context, question, coded candidate answers, and an answer prefix. Starting from a 64-layer Qwen hybrid decoder, GLiDE removes causal masking from its 16 full-attention layers, enabling bidirectional interactions while retaining causal recurrence in the 48 Gated DeltaNet layers. A dedicated 255-way readout scores the final hidden state, and a softmax over the offered options produces a normalized probability distribution. Decisions are computed in a single forward pass, without generating tokens or intermediate reasoning. Appendix C details the output semantics and deployment policies.
Model
Full ↑
Same-skill ↑
New-domain ↑
Gen. gap
ECE (%) ↓
Latency (ms) ↓
GLiDE V1.2
71.52
68.31
76.32
−0.47
2.0
92.9
Jeffan-31B
69.75
65.86
75.58
−3.38
4.7
121.0
mammoth-1
68.44
65.98
72.14
−6.90
4.1
220.1
Decider v1.2
67.98
63.99
73.98
+0.24
5.5
144.4
d3-turbo v1.1
67.31
63.98
72.31
−4.31
5.2
190.5
Jev 1.14
60.24
58.91
62.24
−0.46
8.0
196.0 †
Table 1: Decision Index comparison (edition 0.4.1, 22 October 2026). Full is the hidden-set ranking score; Same-skill and New-domain are its components. Gen. gap is Full minus public score; closer to zero means that public and hidden scores agree. ECE measures calibration; latency is measured on one RTX PRO 6000 GPU ( † hosted API).
Training characteristic
Value
Final-stage examples
374,720
Distinct questions
> 1.6M
Training tokens
∼ 2.3B
Task families
> 500
Screened domains
267
Table 2: GLiDE training data overview. Training combines existing datasets, procedural generation, and LLM-generated decision examples. Totals cover all training stages unless otherwise specified.
Figure 3: Hugging Face Decision Index, edition 0.4.1 (22 October 2026; Passos, 2026a ). Full score on the hidden sets for the top 12 of 225 models, plus Jev 1.14 ( TypeSafe AI, 2026 ) as reference. =3 and =4 denote ranks shared under the board’s tie rule; “indep.” denotes an independent developer. The axis starts at 55. Scored by the board’s maintainers on hidden test sets.
Configuration
Dev. ↑
Acc. ↑
Sens. ↓
Stage 1 (no training)
59.36
–
1.36
Causal + gold labels
60.42
87.01
1.25
Non-causal + gold
61.78
88.38
0.22
Non-causal + soft targets
62.59
89.16
−0.18
+ 30% format augmentation
62.22
88.67
–
Table 3: Single-pass conversion ablations. All trained variants use 125K examples and one seed. Dev. is a composite development score; Acc. is held-out accuracy (%); Sens. measures score loss under input-format perturbations. Negative Sens. means that the score improved under perturbation; – denotes not measured.
Benchmark
GLiDE V1.2
Best open
Jev 1.13
JevBench (accuracy)
93.07
93.94
86.58
Clinical held-out
97.01
96.56
–
SciFact (macro-F1)
85.63
84.05
–
Regression watch
84.88
84.10
–
Table 4: Complementary development measurements
Figure 4: GLiDE V1.2 compared with the other models on the Hugging Face Decision Index, edition 0.4.1. Scored by the board’s maintainers on hidden test sets. a , Calibration error against Full score, for models scoring above 50. b , Full score against median latency on one GPU. c , Stated confidence against measured accuracy for GLiDE V1.2 ; larger markers hold more answers.
Model
Developer
v1
v2
v2.1
Drex Max v1.1
Nace.AI
63.78
73.39
72.62
SubQ Snap 1.2
Subquadratic
–
–
72.58
GLiDE V1.2
Fastino
65.01
72.83
72.52
Mammoth 27B
Baseten
–
72.45
71.36
d1-ultra
Liquid AI
65.25
70.45
70.58
SubQ Snap 1.1
Subquadratic
65.00
69.17
67.92
Table 5: Artificial Analysis Decision Index, versions 1, 2 and 2.1. Scores are those published by Artificial Analysis, retrieved on 5, 8 and 15 November 2026. The leaderboard displays them as whole numbers. An underlined score displays as the highest number on its version. Rows are ordered by version 2.1 score; a dash means the model was not listed on that version. Shown are every model within one point of the highest score on any version, plus Jev and the models of Google, Microsoft and OpenAI. Appendix F lists all models. Higher is better.
Confidence at least
Answers kept (%)
Accuracy (%)
0 (all answers)
100.0
81.5
0.5
90.8
86.2
0.6
82.9
89.5
0.7
76.1
92.0
0.8
67.9
95.0
0.9
56.0
97.4
Table 6: Accuracy when only confident answers are accepted. Computed for GLiDE V1.2 from the board’s calibration sample.
Model
ECE
Conf. − acc.
Wrong, conf. ≥ 0.95
Brier
GLiDE V1.2
2.0
+1.1
0.72
0.257
StartLux v1.1
2.6
+2.5
1.28
0.239
mammoth-1
4.1
+3.9
1.37
0.238
Jeffan-31B
4.7
+4.7
1.64
0.249
FlexDM
4.4
+3.5
0.25
0.355
Jev 1.14
8.0
+7.3
2.65
0.357
Table 7: Calibration on the board’s sample Lower is better, except for Conf. − acc., where closer to zero is better; a positive value means overconfidence. ECE and the fourth column are in %. The fourth column is the share of answers that are wrong despite a confidence of at least 0.95.
Figure 5: Every GLiDE model descends from one lineage of weights. Filled circles are fine-tuned checkpoints, ⊕ marks a weight average, and the arc marks the recurrent loop, which needs no training. Dashed lines show where the output distributions of the 27B model are distilled into smaller models. Scores are Full scores on the Hugging Face Decision Index, scored by the board’s maintainers on hidden test sets. “#1 on DI 0.4.1” refers to the board of 22 October 2026.
Figure 6: Recurrent depth. a , GLiDE 27B in one forward pass: the 64-layer hybrid decoder with the causal mask removed from its 16 full-attention layers, the 255-way readout, and two blocks of middle layers that are each applied twice at inference. b , The loop treats a block of layers F as a map and takes damped steps towards its fixed point (Equation 15 ). An undamped step ( η=1 ) overshoots.
Figure 7: The board’s own chart of model size against Full score , with its Pareto option switched on. Screenshot of the Hugging Face Decision Index website ( Passos, 2026b ) , taken on 15 November 2026 and reproduced unchanged. Highlighted points are on the frontier. Figure 8 a redraws the same data. Scored by the board’s maintainers on hidden test sets.
Model
Params
Full
Δ
Latency
ECE
GLiDE 27B
26.1B
73.37
+3.19
122 ms
2.1%
GLiDE 9B
7.9B
62.48
+6.49
86 ms
1.7%
GLiDE 2B
1.9B
43.72
+10.91
37 ms
6.6%
GLiDE 0.8B
0.75B
36.36
+3.89
37 ms
7.6%
GLiDE 0.4B
0.39B
33.84
+4.57
18 ms
4.9%
Table 8: The GLiDE family on the Hugging Face Decision Index (board of 12 November 2026, 300 models). Full is the ranking score on the hidden sets. Δ is the lead over the best other model of equal or smaller size. Latency is the board’s median on one RTX PRO 6000 GPU.
Figure 8: The GLiDE family on the Hugging Face Decision Index (board of 12 November 2026, 300 models). Scored by the board’s maintainers on hidden test sets. a , Full score on the hidden sets against parameters served, for every model with a declared size. The line is the Pareto frontier: a model is on it when no smaller model scores higher. The five GLiDE models (orange) are on it; open circles are the other models on it. b , Calibration error against Full score, for models scoring above 50. Figure 7 is the board’s own version of panel a.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Component
Base LM
GLiDE V1.2
Input
Text prefix
Context, question, options
Full attention (16)
Causal
Bidirectional
Gated DeltaNet (48)
Causal
Causal
Readout
∼ 248K token logits
255 option logits
Prediction
Next token
Option probabilities
Forward passes
One per token
One per decision
Appendix
Table 9: From a language model to GLiDE V1.2 . The full-attention mask and readout change, while Gated DeltaNet layers retain causal recurrence.
Figure 9: How GLiDE V1.2 was made. Each stage continues from the weights of the one before; the Stage 1 reasoning model’s post-thinking answer distribution is one of the soft targets for the single-pass conversion. Stage 4 trains GLiDE V1.1 on the rebuilt mixture with routed, gold-anchored soft targets and releases the average of two seeds.
Model
Developer
v1
v2
v2.1
Drex Max v1.1
Nace.AI
63.78
73.39
72.62
SubQ Snap 1.2
Subquadratic
–
–
72.58
GLiDE V1.2
Fastino
65.01
72.83
72.52
Mammoth 27B
Baseten
–
72.45
71.36
d1-ultra
Liquid AI
65.25
70.45
70.58
Decider v1.3
Perplexity
–
–
70.41
Appendix
Table 10: Artificial Analysis Decision Index, versions 1, 2 and 2.1: all decision models, ordered by their latest score. Our model is in bold. A dash means the model was not listed on that version.
LLM decision-making studies how language models choose, act, seek information, and allocate resources under goals, uncertainty, constraints, and social pressures.