Skip to main content
BenchLM
Data

Cloudflare Decision Index 0.2.1: ACOS

We show this table for reference; we do not rank on it.

Published Cloudflare and community decision-model configurations.

Evaluation results published by Cloudflare and upstream community contributors.

per-review F1 on Cloudflare Decision Index 0.2.1: ACOS — October 1, 2026 capture

We mirror the published per-review f1 view for Cloudflare Decision Index 0.2.1: ACOS. simple-jev · Qwen3.8-27B (featherless) leads the public snapshot at 35.6%, followed by Clef (33.3%) and Jev (29.5%). We do not use these results to rank models overall.

73 configurationsDecision ModelsDated mixed-source configurationsDisplay onlyUpdated October 1, 2026 capture

per-review F1 table (73 configurations)

per-review F1 results for Cloudflare Decision Index 0.2.1: ACOS
RankModel / configurationScoreParameters (B)Open / closed
1simple-jev · Qwen3.8-27B (featherless)Creator not reportedUpstream community result; inference technique; 38/38 index tasks; median 373 ms; p95 2796.8 ms
35.6%
Not reportedUnknown
2ClefCloudflareCloudflare self-reported; Routing head + LoRA; 36/38 index tasks; median 209.3 ms; p95 238.6 ms
33.3%
Not reportedUnknown
3JevTypeSafeUpstream community result; Hosted API (closed); 38/38 index tasks; median 524.1 ms; p95 536 ms
29.5%
Not reportedUnknown
4djevCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 84.4 ms; p95 211.2 ms
27.5%
Not reportedUnknown
5Decider 35B-A3B [NVFP4]Creator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 101.4 ms; p95 210.9 ms
27.2%
Not reportedUnknown
6Surogate Rune 26B-A4B v3 [bf16]Creator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 120.5 ms; p95 682.8 ms
26.8%
Not reportedUnknown
7Clef-flashCloudflareCloudflare self-reported; Routing head + LoRA; 36/38 index tasks; median 38.8 ms; p95 122.4 ms
25.9%
Not reportedUnknown
8JoshuaSP diffusiongemma (open-jev)Creator not reportedUpstream community result; inference technique; 38/38 index tasks; median 260.4 ms; p95 537.3 ms
24.5%
Not reportedUnknown
9Decider chat · Qwen3.6-27BCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 83.6 ms; p95 965.6 ms
24.4%
Not reportedUnknown
10Bespoke Nimble 9B v2Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 77.3 ms; p95 621.4 ms
23.1%
Not reportedUnknown
11JPT-9BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 148.6 ms; p95 461.9 ms
22.8%
Not reportedUnknown
12Eikos-27B [FP8]Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 129.7 ms; p95 509.8 ms
22.4%
Not reportedUnknown
13JevfireCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 89.6 ms; p95 447.5 ms
22.4%
Not reportedUnknown
14Jebadiah 27BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 110.4 ms; p95 591.1 ms
20.8%
Not reportedUnknown
15Solomon v1.1Creator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 223.9 ms; p95 1176.8 ms
20.7%
Not reportedUnknown
16Winnow-E4B [Q8_0]Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 45 ms; p95 188.3 ms
20.6%
Not reportedUnknown
17AutoJev-27BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 101.4 ms; p95 1052.5 ms
20.4%
Not reportedUnknown
18reflex 27B [FP8 · wide choice]Creator not reportedUpstream community result; inference technique; 38/38 index tasks; median 108.3 ms; p95 1239.7 ms
20.0%
Not reportedUnknown
19JPT-4BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 139.1 ms; p95 405.7 ms
20.0%
Not reportedUnknown
20Decider 4BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 12.6 ms; p95 188.5 ms
19.2%
Not reportedUnknown
21Decider chat · Gemma-4-31BCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 108.5 ms; p95 1114.7 ms
18.8%
Not reportedUnknown
22Kev 9BCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 51.4 ms; p95 187.9 ms
18.3%
Not reportedUnknown
23XorCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 139.9 ms; p95 419.9 ms
17.3%
Not reportedUnknown
24Hopper (G) 1.2Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 23.3 ms; p95 238.2 ms
16.4%
Not reportedUnknown
25Decision 1.0 LuxCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 51 ms; p95 347.5 ms
16.3%
Not reportedUnknown
26Jev-OmniCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 54.9 ms; p95 627.9 ms
16.0%
Not reportedUnknown
27Intern-Decision-4BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 44.2 ms; p95 115.4 ms
15.9%
Not reportedUnknown
28Winnow-12B [Q8_0]Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 72.5 ms; p95 356.2 ms
15.5%
Not reportedUnknown
29JevK5Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 22 ms; p95 226.3 ms
15.1%
Not reportedUnknown
30razorback16 openjev diffusiongemma (NVFP4, vLLM) [one read, NVFP4]Creator not reportedUpstream community result; inference technique; 38/38 index tasks; median 37.7 ms; p95 117.8 ms
14.8%
Not reportedUnknown
31mmastrac diffusiongemma (vLLM PR 57250)Creator not reportedUpstream community result; inference technique; 38/38 index tasks; median 126.7 ms; p95 274.6 ms
14.4%
Not reportedUnknown
32openvonsCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 21.2 ms; p95 113.3 ms
14.2%
Not reportedUnknown
33SemIfCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 113.1 ms; p95 214.6 ms
13.5%
Not reportedUnknown
34JobeCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 53.5 ms; p95 2910.3 ms
13.4%
Not reportedUnknown
35Jet v6.2Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 46.8 ms; p95 371.1 ms
13.0%
Not reportedUnknown
36Kev 4BCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 52.1 ms; p95 141.1 ms
12.3%
Not reportedUnknown
37open-jev (pngwn)Creator not reportedUpstream community result; LoRA; 38/38 index tasks; median 112.3 ms; p95 724.1 ms
12.1%
Not reportedUnknown
38Decision 1.0 SolCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 38.1 ms; p95 101 ms
11.5%
Not reportedUnknown
39Tev1-4B-experimentalCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 35.8 ms; p95 166 ms
10.3%
Not reportedUnknown
40mini-jevCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 66.9 ms; p95 178 ms
9.1%
Not reportedUnknown
41Bosun v3.1 1.7BCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 40.3 ms; p95 173.5 ms
8.8%
Not reportedUnknown
42Decider 2B [FP8]Creator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 8.1 ms; p95 134.9 ms
7.9%
Not reportedUnknown
43Kev 0.8BCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 41.6 ms; p95 95.9 ms
7.8%
Not reportedUnknown
44JPT-0.8BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 117.5 ms; p95 341.2 ms
7.3%
Not reportedUnknown
45Decision 1.0 NoxCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 53.2 ms; p95 242.1 ms
7.3%
Not reportedUnknown
46this-that 1.2Creator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 44.3 ms; p95 57.2 ms
7.3%
Not reportedUnknown
47levCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 70.8 ms; p95 687.7 ms
7.1%
Not reportedUnknown
48Metask-Jev-4BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 57.3 ms; p95 369.4 ms
6.8%
Not reportedUnknown
49LFM2.5-2.6B-RLCDCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 39.3 ms; p95 95.4 ms
5.6%
Not reportedUnknown
50Bosun v3.1 0.6BCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 38.7 ms; p95 107.3 ms
5.6%
Not reportedUnknown
51Decision 1.0 EosCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 39.7 ms; p95 84.3 ms
5.5%
Not reportedUnknown
52Tev1-0.8B-experimentalCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 28.5 ms; p95 133.9 ms
5.4%
Not reportedUnknown
53NeoHorse-Jev-4BCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 49 ms; p95 273.9 ms
5.4%
Not reportedUnknown
54Intern-Decision-0.8BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 33.7 ms; p95 39.2 ms
4.6%
Not reportedUnknown
55Qwen-2.5-1B-RLCDCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 43.8 ms; p95 75.2 ms
4.6%
Not reportedUnknown
56Intern-Decision-2BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 33.5 ms; p95 58 ms
4.0%
Not reportedUnknown
57LavoirCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 20 ms; p95 49.5 ms
3.9%
Not reportedUnknown
58Decision 1.0 KaiCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 30.4 ms; p95 106.8 ms
3.8%
Not reportedUnknown
59VerdictCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 11.4 ms; p95 60.1 ms
3.6%
Not reportedUnknown
60LayaCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 5.8 ms; p95 222.5 ms
3.5%
Not reportedUnknown
61MoJevCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 46.4 ms; p95 55.1 ms
3.2%
Not reportedUnknown
62jeffCreator not reportedUpstream community result; inference technique; 38/38 index tasks; median 21.8 ms; p95 67.6 ms
3.2%
Not reportedUnknown
63Julia 1Creator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 5.8 ms; p95 15.3 ms
3.1%
Not reportedUnknown
64CLM-v0.1-8BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 46.8 ms; p95 130.9 ms
3.1%
Not reportedUnknown
65GLiNER 2.5 baseCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 14.1 ms; p95 62.1 ms
3.1%
Not reportedUnknown
66Decision 1.0 LexCreator not reportedUpstream community result; head / adapter; 38/38 index tasks; median 29.8 ms; p95 106 ms
3.1%
Not reportedUnknown
67GLiNER 2.5 smallCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 13.6 ms; p95 35.2 ms
3.1%
Not reportedUnknown
68LFM2.5-350M-RLCDCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 26.7 ms; p95 174.3 ms
3.1%
Not reportedUnknown
69system-one-gemmaCreator not reportedUpstream community result; LoRA + head; 38/38 index tasks; median 31.9 ms; p95 748 ms
3.1%
Not reportedUnknown
70GLiNER 2.5 multilingualCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 14 ms; p95 92.4 ms
3.0%
Not reportedUnknown
71Lumma-Fev-0.1BCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 20.9 ms; p95 112.5 ms
1.1%
Not reportedUnknown
72GLiNER2.5-DecideCreator not reportedUpstream community result; full fine-tune; 38/38 index tasks; median 23.3 ms; p95 228.6 ms
0.0%
Not reportedUnknown
73Lumma-Fev-0.6BCreator not reportedUpstream community result; LoRA; 38/38 index tasks; median 21.3 ms; p95 219.7 ms
0.0%
Not reportedUnknown

How to read this source comparison

The source combines Cloudflare self-reported Clef runs with upstream community configurations. Each row retains its source engine and evidence label; model names alone do not establish equivalent serving settings.

The 0.2.1 composite uses 38 panel benchmarks grouped into five weighted areas. It applies chance correction; ForecastBench uses its Brier transformation. Additional task views retain the source metric and panel-inclusion metadata. The snapshot lists 48 task metrics, while the launch refers to 43 evaluations including latency rows.

Clef and Clef-Flash each cover 36 of 38 index tasks; HLE and iSarcasmEval are missing. Missing values are not inserted as zero. The composite is retained as published without recomputing it or filling gaps.

Community results use the upstream September 28 snapshot, which declares one NVIDIA RTX PRO 6000. Cloudflare run hardware is not established by this artifact. Latency comparisons across these configurations do not isolate model speed. The October 1 date marks capture, not evaluation.

These views remain separate from JevBench and canonical provider benchmark results. They do not enter overall or category rankings. Equal scores do not establish statistical ties.

The published Cloudflare Decision Index 0.2.1: ACOS snapshot places simple-jev · Qwen3.8-27B (featherless) first at 35.6%. The third row is 6.1 points behind. The broader top-10 range is 12.4 points, so the table still separates the published systems.

73 configurations are shown for Cloudflare Decision Index 0.2.1: ACOS. The benchmark falls in the Decision Models category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Cloudflare Decision Index 0.2.1: ACOS is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Cloudflare Decision Index 0.2.1: ACOS

Year

2026

Freshness and provenance

Version

Cloudflare comparison on Decision Index 0.2.1

Refresh cadence

Reviewed dated source capture

Staleness state

Dated mixed-source configurations

Question availability

Upstream tasks and terms; aggregate scores only

Dated mixed-source configurationsDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does Cloudflare Decision Index 0.2.1: ACOS measure?

Published Cloudflare and community decision-model configurations.

Which model leads the published Cloudflare Decision Index 0.2.1: ACOS snapshot?

simple-jev · Qwen3.8-27B (featherless) currently leads the published Cloudflare Decision Index 0.2.1: ACOS snapshot with 35.6% per-review f1. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Cloudflare Decision Index 0.2.1: ACOS?

The October 1, 2026 capture snapshot contains 73 AI models.

Last updated: October 1, 2026 capture · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 5,600+ readers.

One email each week. Unsubscribe anytime.