omp-llm-role 1.1.0 → 1.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +75 -13
- package/docs/dev/architecture.md +35 -11
- package/docs/dev/ci.md +21 -1
- package/docs/dev/current-state.md +99 -27
- package/docs/dev/data-sources.md +33 -4
- package/docs/dev/explorer.md +126 -21
- package/docs/dev/quirks.md +32 -0
- package/docs/dev/releasing.md +63 -32
- package/docs/dev/scoring.md +153 -39
- package/docs/dev/testing.md +112 -24
- package/docs/dev/writes-and-state.md +86 -0
- package/docs/llm-role-rankings.md +126 -126
- package/package.json +92 -22
- package/src/agent-create.ts +4 -2
- package/src/availability.ts +87 -9
- package/src/cli/create-role.ts +1 -1
- package/src/engine.ts +190 -78
- package/src/explorer/boot.ts +43 -1
- package/src/explorer/explain.ts +113 -10
- package/src/explorer/levers.ts +100 -0
- package/src/explorer/pool.ts +46 -0
- package/src/explorer/server.ts +107 -23
- package/src/extension.ts +189 -16
- package/src/features.ts +9 -7
- package/src/provider-display.ts +67 -0
- package/src/settings.ts +39 -2
- package/src/updater.ts +97 -14
- package/src/usage-ledger.ts +127 -0
- package/web/app.js +156 -1
- package/web/style.css +3 -0
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
llm-stats.com best-fit ranking per omp model role —
|
|
1
|
+
llm-stats.com best-fit ranking per omp model role — 408 models, 2026-10-19
|
|
2
2
|
Value ranking per role: each metric is cardinal-normalized with fixed anchors
|
|
3
3
|
(no ranks): llm-stats index_* affine (v+20)/80 (interval scale, observed −16..+60),
|
|
4
4
|
benchmarks chance-anchored pass rates, throughput log-anchored 10..300 tok/s.
|
|
@@ -21,178 +21,178 @@ agon=Design Arena `agents/agon_webapps` Elo from the same endpoint: context
|
|
|
21
21
|
only, unweighted (22/87 of the designer pool, below the ~35–40% coverage
|
|
22
22
|
bar at which a metric earns weight).
|
|
23
23
|
★ = Pareto-frontier: no eligible model is both cheaper and better (q).
|
|
24
|
-
Throughput + price: OpenRouter per-provider routes under the default price-based routing (weight 1/price² over stable standard-tier providers; p50 tok/s of routed traffic; $/M 3:1 in:out), throughput
|
|
24
|
+
Throughput + price: OpenRouter per-provider routes under the default price-based routing (weight 1/price² over stable standard-tier providers; p50 tok/s of routed traffic; $/M 3:1 in:out), throughput 149/408, priced 148; models without OpenRouter throughput or a billed route are not ranked.
|
|
25
25
|
|
|
26
26
|
## @default — Main workhorse: strong general coding-agent quality, sane cost
|
|
27
|
-
eligible:
|
|
27
|
+
eligible: 140 — λ 0.00556 $/quality-point (thinking ×1.857)
|
|
28
28
|
|
|
29
29
|
| # | value | q | model | org | $/M | tok/s | ctx | gen 54.7% | code 18.9% | ag 12.6% | tool 10.5% | tput 3.2% |
|
|
30
30
|
| -: | ----: | ----: | --------------------- | ----------- | ----: | ----: | ---: | --------: | ---------: | -------: | ---------: | --------: |
|
|
31
|
-
| 1 | 0.
|
|
32
|
-
| 2 | 0.
|
|
33
|
-
| 3 | 0.794 | 0.
|
|
34
|
-
| 4 | 0.
|
|
35
|
-
| 5 | 0.
|
|
36
|
-
| 6 | 0.
|
|
37
|
-
| 7 | 0.
|
|
38
|
-
| 8 | 0.
|
|
39
|
-
| 9 | 0.
|
|
40
|
-
| 10 | 0.
|
|
31
|
+
| 1 | 0.807 | 0.809 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.483 | 0.146 | 0.093 | 0.069 | 0.019 |
|
|
32
|
+
| 2 | 0.799 | 0.841 | ★ Gemini 4 Argon | Google | $7.65 | 38 | — | 0.516 | 0.149 | 0.096 | 0.068 | 0.012 |
|
|
33
|
+
| 3 | 0.794 | 0.806 | GLM-5.3 | Zhipu AI | $2.09 | 73 | 1.0M | 0.488 | 0.142 | 0.090 | 0.067 | 0.018 |
|
|
34
|
+
| 4 | 0.789 | 0.810 | ★ Muse Spark 1.3 | Meta | $3.71 | 70 | 1.0M | 0.495 | 0.139 | 0.091 | 0.067 | 0.018 |
|
|
35
|
+
| 5 | 0.776 | 0.793 | DeepSeek-V4-Pro-0813 | DeepSeek | $3.09 | 78 | 1.0M | 0.484 | 0.139 | 0.088 | 0.063 | 0.019 |
|
|
36
|
+
| 6 | 0.776 | 0.781 | MiMo-V2.6-Pro | Xiaomi | $1.01 | 29 | 1.0M | 0.476 | 0.141 | 0.089 | 0.066 | 0.010 |
|
|
37
|
+
| 7 | 0.773 | 0.811 | ★ Kimi K3 | Moonshot AI | $6.81 | 52 | 1.0M | 0.494 | 0.144 | 0.091 | 0.067 | 0.015 |
|
|
38
|
+
| 8 | 0.766 | 0.809 | GPT-6.1 Sol | OpenAI | $7.89 | 40 | 1.1M | 0.506 | 0.141 | 0.092 | 0.057 | 0.013 |
|
|
39
|
+
| 9 | 0.764 | 0.777 | Hy4 preview | Tencent | $2.32 | 37 | — | 0.478 | 0.137 | 0.087 | 0.063 | 0.012 |
|
|
40
|
+
| 10 | 0.763 | 0.765 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.473 | 0.123 | 0.087 | 0.065 | 0.018 |
|
|
41
41
|
|
|
42
42
|
## @smol — Fast lightweight model: cheap and quick, still competent
|
|
43
|
-
eligible:
|
|
44
|
-
|
|
45
|
-
| # | value | q | model | org
|
|
46
|
-
| -: | ----: | ----: | ---------------------------- |
|
|
47
|
-
| 1 | 0.
|
|
48
|
-
| 2 | 0.
|
|
49
|
-
| 3 | 0.
|
|
50
|
-
| 4 | 0.
|
|
51
|
-
| 5 | 0.
|
|
52
|
-
| 6 | 0.
|
|
53
|
-
| 7 | 0.
|
|
54
|
-
| 8 | 0.
|
|
55
|
-
| 9 | 0.
|
|
56
|
-
| 10 | 0.
|
|
43
|
+
eligible: 140 — λ 0.04091 $/quality-point
|
|
44
|
+
|
|
45
|
+
| # | value | q | model | org | $/M | tok/s | ctx | tput 40% | gen 28.6% | code 17.1% | tool 14.3% |
|
|
46
|
+
| -: | ----: | ----: | ---------------------------- | --------------------- | ----: | ----: | ---: | -------: | --------: | ---------: | ---------: |
|
|
47
|
+
| 1 | 0.706 | 0.714 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.20 | 75 | 1.0M | 0.237 | 0.252 | 0.132 | 0.094 |
|
|
48
|
+
| 2 | 0.687 | 0.713 | Inkling-Small | Thinking Machines Lab | $0.64 | 167 | 524k | 0.331 | 0.208 | 0.104 | 0.070 |
|
|
49
|
+
| 3 | 0.669 | 0.671 | ★ Ling 3.0 Flash | InclusionAI | $0.04 | 140 | 131k | 0.310 | 0.200 | 0.096 | 0.065 |
|
|
50
|
+
| 4 | 0.662 | 0.744 | ★ Muse Spark 1.1 | Meta | $2.00 | 127 | 1.0M | 0.298 | 0.245 | 0.113 | 0.087 |
|
|
51
|
+
| 5 | 0.661 | 0.669 | GLM-5.3-Flash | Zhipu AI | $0.18 | 66 | 1.0M | 0.223 | 0.247 | 0.112 | 0.088 |
|
|
52
|
+
| 6 | 0.661 | 0.707 | GLM-5.3 | Zhipu AI | $1.12 | 73 | 1.0M | 0.233 | 0.255 | 0.129 | 0.091 |
|
|
53
|
+
| 7 | 0.652 | 0.670 | DeepSeek-V4-Flash-Vision-Exp | DeepSeek | $0.43 | 83 | 1.0M | 0.249 | 0.231 | 0.115 | 0.075 |
|
|
54
|
+
| 8 | 0.652 | 0.733 | Muse Spark 1.2 | Meta | $2.00 | 224 | 1.0M | 0.366 | 0.204 | 0.102 | 0.062 |
|
|
55
|
+
| 9 | 0.647 | 0.667 | GPT-5.6 Luna | OpenAI | $0.47 | 80 | 1.1M | 0.244 | 0.229 | 0.117 | 0.076 |
|
|
56
|
+
| 10 | 0.643 | 0.707 | Gemini 3.8 Flash | Google | $1.57 | 95 | 1.0M | 0.264 | 0.247 | 0.119 | 0.076 |
|
|
57
57
|
|
|
58
58
|
## @slow — Most capable model for hard problems; cost and speed as tiebreakers
|
|
59
|
-
eligible:
|
|
59
|
+
eligible: 140 — λ 0.00263 $/quality-point (thinking ×2.714)
|
|
60
60
|
|
|
61
61
|
| # | value | q | model | org | $/M | tok/s | ctx | gen 63.2% | code 18.9% | ag 13.7% | tput 4.2% |
|
|
62
62
|
| -: | ----: | ----: | --------------------- | ----------- | ----: | ----: | ---: | --------: | ---------: | -------: | --------: |
|
|
63
|
-
| 1 | 0.
|
|
64
|
-
| 2 | 0.
|
|
65
|
-
| 3 | 0.
|
|
66
|
-
| 4 | 0.
|
|
67
|
-
| 5 | 0.
|
|
68
|
-
| 6 | 0.
|
|
69
|
-
| 7 | 0.
|
|
70
|
-
| 8 | 0.
|
|
71
|
-
| 9 | 0.
|
|
72
|
-
| 10 | 0.
|
|
63
|
+
| 1 | 0.835 | 0.865 | ★ Gemini 4 Argon | Google | $11.2 | 38 | — | 0.595 | 0.149 | 0.104 | 0.016 |
|
|
64
|
+
| 2 | 0.827 | 0.829 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.54 | 75 | 1.0M | 0.558 | 0.146 | 0.100 | 0.025 |
|
|
65
|
+
| 3 | 0.819 | 0.827 | GLM-5.3 | Zhipu AI | $3.05 | 73 | 1.0M | 0.563 | 0.142 | 0.098 | 0.025 |
|
|
66
|
+
| 4 | 0.818 | 0.833 | ★ Muse Spark 1.3 | Meta | $5.43 | 70 | 1.0M | 0.572 | 0.139 | 0.099 | 0.024 |
|
|
67
|
+
| 5 | 0.812 | 0.842 | GPT-6.1 Sol | OpenAI | $11.5 | 40 | 1.1M | 0.584 | 0.141 | 0.100 | 0.017 |
|
|
68
|
+
| 6 | 0.806 | 0.833 | Kimi K3 | Moonshot AI | $9.95 | 52 | 1.0M | 0.570 | 0.144 | 0.098 | 0.020 |
|
|
69
|
+
| 7 | 0.806 | 0.818 | DeepSeek-V4-Pro-0813 | DeepSeek | $4.51 | 78 | 1.0M | 0.559 | 0.139 | 0.095 | 0.025 |
|
|
70
|
+
| 8 | 0.796 | 0.800 | MiMo-V2.6-Pro | Xiaomi | $1.47 | 29 | 1.0M | 0.549 | 0.141 | 0.097 | 0.013 |
|
|
71
|
+
| 9 | 0.792 | 0.852 | GPT-5.6 Sol | OpenAI | $22.9 | 54 | 1.1M | 0.580 | 0.150 | 0.101 | 0.021 |
|
|
72
|
+
| 10 | 0.790 | 0.798 | Hy4 preview | Tencent | $3.39 | 37 | — | 0.552 | 0.137 | 0.094 | 0.016 |
|
|
73
73
|
|
|
74
74
|
## @vision — Image understanding: vision index dominates
|
|
75
|
-
eligible:
|
|
75
|
+
eligible: 73 — λ 0.00682 $/quality-point (thinking ×1.857)
|
|
76
76
|
|
|
77
77
|
| # | value | q | model | org | $/M | tok/s | ctx | vis 54.2% | gen 20.8% | rea 15.6% | code 6.3% | tput 3.1% |
|
|
78
78
|
| -: | ----: | ----: | --------------------- | ------------------------- | ----: | ----: | ---: | --------: | --------: | --------: | --------: | --------: |
|
|
79
|
-
| 1 | 0.
|
|
80
|
-
| 2 | 0.
|
|
81
|
-
| 3 | 0.727 | 0.
|
|
82
|
-
| 4 | 0.
|
|
83
|
-
| 5 | 0.
|
|
84
|
-
| 6 | 0.715 | 0.
|
|
85
|
-
| 7 | 0.
|
|
86
|
-
| 8 | 0.
|
|
87
|
-
| 9 | 0.
|
|
88
|
-
| 10 | 0.
|
|
79
|
+
| 1 | 0.733 | 0.786 | ★ Gemini 4 Argon | Google | $7.65 | 38 | — | 0.385 | 0.196 | 0.143 | 0.049 | 0.012 |
|
|
80
|
+
| 2 | 0.728 | 0.731 | ★ Qwen3.8 Flash | Alibaba Cloud / Qwen Team | $0.43 | 47 | 1.0M | 0.363 | 0.178 | 0.133 | 0.042 | 0.014 |
|
|
81
|
+
| 3 | 0.727 | 0.730 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.345 | 0.184 | 0.134 | 0.048 | 0.018 |
|
|
82
|
+
| 4 | 0.724 | 0.750 | ★ Muse Spark 1.1 | Meta | $3.71 | 127 | 1.0M | 0.371 | 0.179 | 0.136 | 0.041 | 0.023 |
|
|
83
|
+
| 5 | 0.722 | 0.768 | ★ Kimi K3 | Moonshot AI | $6.81 | 52 | 1.0M | 0.378 | 0.188 | 0.139 | 0.048 | 0.015 |
|
|
84
|
+
| 6 | 0.715 | 0.769 | GPT-6.1 Sol | OpenAI | $7.89 | 40 | 1.1M | 0.377 | 0.193 | 0.140 | 0.047 | 0.013 |
|
|
85
|
+
| 7 | 0.714 | 0.734 | ★ Gemini 3.8 Flash | Google | $2.91 | 95 | 1.0M | 0.361 | 0.180 | 0.129 | 0.043 | 0.021 |
|
|
86
|
+
| 8 | 0.713 | 0.715 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.344 | 0.180 | 0.133 | 0.041 | 0.017 |
|
|
87
|
+
| 9 | 0.702 | 0.707 | Qwen3.8-27B | Alibaba Cloud / Qwen Team | $0.72 | 55 | 262k | 0.358 | 0.168 | 0.126 | 0.039 | 0.016 |
|
|
88
|
+
| 10 | 0.697 | 0.717 | Gemini 3.7 Flash | Google | $2.87 | 86 | 1.0M | 0.353 | 0.176 | 0.127 | 0.041 | 0.020 |
|
|
89
89
|
|
|
90
90
|
## @plan — Planning: reasoning and long-context coherence, priced so the cheapest capable planner wins
|
|
91
|
-
eligible:
|
|
91
|
+
eligible: 140 — λ 0.01667 $/quality-point (thinking ×1.857)
|
|
92
92
|
|
|
93
93
|
| # | value | q | model | org | $/M | tok/s | ctx | gen 80% | lc 15.6% | tput 4.4% |
|
|
94
94
|
| -: | ----: | ----: | --------------------- | ------------------------- | ----: | ----: | ---: | ------: | -------: | --------: |
|
|
95
|
-
| 1 | 0.
|
|
96
|
-
| 2 | 0.
|
|
97
|
-
| 3 | 0.
|
|
98
|
-
| 4 | 0.
|
|
99
|
-
| 5 | 0.
|
|
100
|
-
| 6 | 0.
|
|
101
|
-
| 7 | 0.
|
|
102
|
-
| 8 | 0.
|
|
103
|
-
| 9 | 0.
|
|
104
|
-
| 10 | 0.
|
|
95
|
+
| 1 | 0.789 | 0.851 | ★ Muse Spark 1.3 | Meta | $3.71 | 70 | 1.0M | 0.724 | 0.101 | 0.025 |
|
|
96
|
+
| 2 | 0.774 | 0.781 | ★ Qwen3.8 Flash | Alibaba Cloud / Qwen Team | $0.43 | 47 | 1.0M | 0.682 | 0.079 | 0.020 |
|
|
97
|
+
| 3 | 0.764 | 0.813 | ★ Gemini 3.8 Flash | Google | $2.91 | 95 | 1.0M | 0.692 | 0.091 | 0.029 |
|
|
98
|
+
| 4 | 0.757 | 0.763 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.707 | 0.030 | 0.026 |
|
|
99
|
+
| 5 | 0.755 | 0.802 | ★ Gemini 3.7 Flash | Google | $2.87 | 86 | 1.0M | 0.676 | 0.098 | 0.028 |
|
|
100
|
+
| 6 | 0.752 | 0.790 | ★ Hy4 preview | Tencent | $2.32 | 37 | — | 0.699 | 0.075 | 0.017 |
|
|
101
|
+
| 7 | 0.742 | 0.870 | ★ Gemini 4 Argon | Google | $7.65 | 38 | — | 0.754 | 0.098 | 0.017 |
|
|
102
|
+
| 8 | 0.740 | 0.746 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.691 | 0.030 | 0.025 |
|
|
103
|
+
| 9 | 0.735 | 0.749 | GPT-5.6 Luna | OpenAI | $0.88 | 80 | 1.1M | 0.642 | 0.080 | 0.027 |
|
|
104
|
+
| 10 | 0.735 | 0.769 | GLM-5.3 | Zhipu AI | $2.09 | 73 | 1.0M | 0.713 | 0.030 | 0.026 |
|
|
105
105
|
|
|
106
106
|
## @commit — Commit messages: cheap and fast with decent general quality
|
|
107
|
-
eligible:
|
|
108
|
-
|
|
109
|
-
| # | value | q | model
|
|
110
|
-
| -: | ----: | ----: |
|
|
111
|
-
| 1 | 0.
|
|
112
|
-
| 2 | 0.
|
|
113
|
-
| 3 | 0.
|
|
114
|
-
| 4 | 0.
|
|
115
|
-
| 5 | 0.
|
|
116
|
-
| 6 | 0.
|
|
117
|
-
| 7 | 0.
|
|
118
|
-
| 8 | 0.692 | 0.
|
|
119
|
-
| 9 | 0.
|
|
120
|
-
| 10 | 0.
|
|
107
|
+
eligible: 140 — λ 0.04091 $/quality-point
|
|
108
|
+
|
|
109
|
+
| # | value | q | model | org | $/M | tok/s | ctx | tput 41.5% | gen 43.1% | code 15.4% |
|
|
110
|
+
| -: | ----: | ----: | ---------------------------- | --------------------- | ----: | ----: | ---: | ---------: | --------: | ---------: |
|
|
111
|
+
| 1 | 0.736 | 0.745 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.20 | 75 | 1.0M | 0.246 | 0.380 | 0.118 |
|
|
112
|
+
| 2 | 0.724 | 0.750 | ★ Inkling-Small | Thinking Machines Lab | $0.64 | 167 | 524k | 0.344 | 0.313 | 0.094 |
|
|
113
|
+
| 3 | 0.709 | 0.710 | ★ Ling 3.0 Flash | InclusionAI | $0.04 | 140 | 131k | 0.322 | 0.302 | 0.086 |
|
|
114
|
+
| 4 | 0.699 | 0.781 | ★ Muse Spark 1.1 | Meta | $2.00 | 127 | 1.0M | 0.310 | 0.370 | 0.101 |
|
|
115
|
+
| 5 | 0.697 | 0.779 | Muse Spark 1.2 | Meta | $2.00 | 224 | 1.0M | 0.380 | 0.308 | 0.091 |
|
|
116
|
+
| 6 | 0.696 | 0.703 | GLM-5.3-Flash | Zhipu AI | $0.18 | 66 | 1.0M | 0.231 | 0.372 | 0.100 |
|
|
117
|
+
| 7 | 0.695 | 0.741 | GLM-5.3 | Zhipu AI | $1.12 | 73 | 1.0M | 0.242 | 0.384 | 0.115 |
|
|
118
|
+
| 8 | 0.692 | 0.710 | DeepSeek-V4-Flash-Vision-Exp | DeepSeek | $0.43 | 83 | 1.0M | 0.259 | 0.348 | 0.103 |
|
|
119
|
+
| 9 | 0.690 | 0.754 | ★ Gemini 3.8 Flash | Google | $1.57 | 95 | 1.0M | 0.275 | 0.373 | 0.106 |
|
|
120
|
+
| 10 | 0.685 | 0.704 | GPT-5.6 Luna | OpenAI | $0.47 | 80 | 1.1M | 0.254 | 0.346 | 0.105 |
|
|
121
121
|
|
|
122
122
|
## @tiny — Background tasks (titles, memory): cheapest and fastest wins
|
|
123
|
-
eligible:
|
|
124
|
-
|
|
125
|
-
| # | value | q | model
|
|
126
|
-
| -: | ----: | ----: |
|
|
127
|
-
| 1 | 0.
|
|
128
|
-
| 2 | 0.765 | 0.
|
|
129
|
-
| 3 | 0.
|
|
130
|
-
| 4 | 0.
|
|
131
|
-
| 5 | 0.
|
|
132
|
-
| 6 | 0.
|
|
133
|
-
| 7 | 0.
|
|
134
|
-
| 8 | 0.
|
|
135
|
-
| 9 | 0.
|
|
136
|
-
| 10 | 0.
|
|
123
|
+
eligible: 140 — λ 0.03333 $/quality-point
|
|
124
|
+
|
|
125
|
+
| # | value | q | model | org | $/M | tok/s | ctx | tput 58.3% | gen 41.7% |
|
|
126
|
+
| -: | ----: | ----: | ----------------------------- | ------------------------- | ----: | ----: | ---: | ---------: | --------: |
|
|
127
|
+
| 1 | 0.769 | 0.782 | ★ Mercury 2 | Inception | $0.38 | 255 | 128k | 0.555 | 0.227 |
|
|
128
|
+
| 2 | 0.765 | 0.831 | ★ Muse Spark 1.2 | Meta | $2.00 | 224 | 1.0M | 0.533 | 0.298 |
|
|
129
|
+
| 3 | 0.764 | 0.786 | ★ Inkling-Small | Thinking Machines Lab | $0.64 | 167 | 524k | 0.483 | 0.303 |
|
|
130
|
+
| 4 | 0.743 | 0.745 | ★ Ling 3.0 Flash | InclusionAI | $0.04 | 140 | 131k | 0.453 | 0.292 |
|
|
131
|
+
| 5 | 0.738 | 0.756 | Gemini 3.1 Flash-Lite | Google | $0.56 | 176 | 1.0M | 0.492 | 0.265 |
|
|
132
|
+
| 6 | 0.726 | 0.793 | Muse Spark 1.1 | Meta | $2.00 | 127 | 1.0M | 0.435 | 0.358 |
|
|
133
|
+
| 7 | 0.717 | 0.768 | Gemini 3.6 Flash | Google | $1.54 | 132 | 1.0M | 0.443 | 0.325 |
|
|
134
|
+
| 8 | 0.707 | 0.713 | DeepSeek-V4.1-Flash | DeepSeek | $0.20 | 75 | 1.0M | 0.345 | 0.368 |
|
|
135
|
+
| 9 | 0.705 | 0.707 | Laguna XS 2.1 | Poolside | $0.07 | 161 | 262k | 0.477 | 0.231 |
|
|
136
|
+
| 10 | 0.702 | 0.743 | Qwen3-235B-A22B-Thinking-2507 | Alibaba Cloud / Qwen Team | $1.21 | 177 | — | 0.493 | 0.250 |
|
|
137
137
|
|
|
138
138
|
## @task — Subagents: agentic + tool calling, moderate cost sensitivity
|
|
139
|
-
eligible:
|
|
139
|
+
eligible: 140 — λ 0.00747 $/quality-point (thinking ×1.857)
|
|
140
140
|
|
|
141
141
|
| # | value | q | model | org | $/M | tok/s | ctx | ag 29.9% | tool 20.7% | code 18.4% | gen 25.3% | tput 5.7% |
|
|
142
142
|
| -: | ----: | ----: | --------------------- | ------------------------- | ----: | ----: | ---: | -------: | ---------: | ---------: | --------: | --------: |
|
|
143
|
-
| 1 | 0.
|
|
144
|
-
| 2 | 0.
|
|
145
|
-
| 3 | 0.
|
|
146
|
-
| 4 | 0.
|
|
147
|
-
| 5 | 0.
|
|
148
|
-
| 6 | 0.
|
|
149
|
-
| 7 | 0.
|
|
150
|
-
| 8 | 0.
|
|
151
|
-
| 9 | 0.
|
|
152
|
-
| 10 | 0.
|
|
143
|
+
| 1 | 0.750 | 0.753 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.219 | 0.136 | 0.141 | 0.223 | 0.034 |
|
|
144
|
+
| 2 | 0.726 | 0.742 | GLM-5.3 | Zhipu AI | $2.09 | 73 | 1.0M | 0.213 | 0.131 | 0.138 | 0.225 | 0.033 |
|
|
145
|
+
| 3 | 0.716 | 0.743 | Muse Spark 1.3 | Meta | $3.71 | 70 | 1.0M | 0.215 | 0.132 | 0.134 | 0.229 | 0.033 |
|
|
146
|
+
| 4 | 0.710 | 0.767 | ★ Gemini 4 Argon | Google | $7.65 | 38 | — | 0.228 | 0.134 | 0.145 | 0.238 | 0.022 |
|
|
147
|
+
| 5 | 0.707 | 0.715 | MiMo-V2.6-Pro | Xiaomi | $1.01 | 29 | 1.0M | 0.211 | 0.129 | 0.137 | 0.220 | 0.018 |
|
|
148
|
+
| 6 | 0.702 | 0.725 | DeepSeek-V4-Pro-0813 | DeepSeek | $3.09 | 78 | 1.0M | 0.208 | 0.124 | 0.135 | 0.224 | 0.035 |
|
|
149
|
+
| 7 | 0.700 | 0.703 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.206 | 0.127 | 0.120 | 0.218 | 0.032 |
|
|
150
|
+
| 8 | 0.692 | 0.743 | Kimi K3 | Moonshot AI | $6.81 | 52 | 1.0M | 0.215 | 0.132 | 0.140 | 0.228 | 0.028 |
|
|
151
|
+
| 9 | 0.688 | 0.691 | Qwen3.8 Flash | Alibaba Cloud / Qwen Team | $0.43 | 47 | 1.0M | 0.198 | 0.127 | 0.124 | 0.216 | 0.026 |
|
|
152
|
+
| 10 | 0.687 | 0.705 | Hy4 preview | Tencent | $2.32 | 37 | — | 0.205 | 0.124 | 0.133 | 0.221 | 0.022 |
|
|
153
153
|
|
|
154
154
|
## @advisor — Advisor/watchdog: deep reasoning over long context
|
|
155
|
-
eligible:
|
|
155
|
+
eligible: 140 — λ 0.01250 $/quality-point (thinking ×1.857)
|
|
156
156
|
|
|
157
157
|
| # | value | q | model | org | $/M | tok/s | ctx | gen 74.3% | lc 12.6% | tput 13.1% |
|
|
158
158
|
| -: | ----: | ----: | --------------------- | ------------------------- | ----: | ----: | ---: | --------: | -------: | ---------: |
|
|
159
|
-
| 1 | 0.
|
|
160
|
-
| 2 | 0.
|
|
161
|
-
| 3 | 0.
|
|
162
|
-
| 4 | 0.
|
|
163
|
-
| 5 | 0.
|
|
164
|
-
| 6 | 0.
|
|
165
|
-
| 7 | 0.
|
|
166
|
-
| 8 | 0.
|
|
167
|
-
| 9 | 0.
|
|
168
|
-
| 10 | 0.
|
|
159
|
+
| 1 | 0.783 | 0.830 | ★ Muse Spark 1.3 | Meta | $3.71 | 70 | 1.0M | 0.673 | 0.082 | 0.075 |
|
|
160
|
+
| 2 | 0.767 | 0.803 | ★ Gemini 3.8 Flash | Google | $2.91 | 95 | 1.0M | 0.643 | 0.073 | 0.087 |
|
|
161
|
+
| 3 | 0.755 | 0.790 | ★ Gemini 3.7 Flash | Google | $2.87 | 86 | 1.0M | 0.628 | 0.079 | 0.083 |
|
|
162
|
+
| 4 | 0.754 | 0.759 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.657 | 0.024 | 0.078 |
|
|
163
|
+
| 5 | 0.752 | 0.757 | Qwen3.8 Flash | Alibaba Cloud / Qwen Team | $0.43 | 47 | 1.0M | 0.634 | 0.063 | 0.060 |
|
|
164
|
+
| 6 | 0.737 | 0.764 | ★ GLM-5.3 | Zhipu AI | $2.09 | 73 | 1.0M | 0.663 | 0.024 | 0.076 |
|
|
165
|
+
| 7 | 0.735 | 0.831 | ★ Gemini 4 Argon | Google | $7.65 | 38 | — | 0.700 | 0.079 | 0.051 |
|
|
166
|
+
| 8 | 0.735 | 0.739 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.642 | 0.024 | 0.073 |
|
|
167
|
+
| 9 | 0.731 | 0.760 | Hy4 preview | Tencent | $2.32 | 37 | — | 0.649 | 0.060 | 0.050 |
|
|
168
|
+
| 10 | 0.730 | 0.741 | GPT-5.6 Luna | OpenAI | $0.88 | 80 | 1.1M | 0.597 | 0.065 | 0.080 |
|
|
169
169
|
|
|
170
170
|
## @designer — Design work: visual/UX judgement on image-capable models
|
|
171
|
-
eligible:
|
|
171
|
+
eligible: 87 — λ 0.01024 $/quality-point (thinking ×1.857)
|
|
172
172
|
|
|
173
173
|
| # | value | q | model | org | $/M | tok/s | ctx | gen 31.3% | code 7.2% | vis 21.7% | tput 18.1% | web 21.7% | agon |
|
|
174
174
|
| -: | ----: | ----: | --------------------- | ----------- | ----: | ----: | ---: | --------: | --------: | --------: | ---------: | --------: | ---: |
|
|
175
|
-
| 1 | 0.
|
|
176
|
-
| 2 | 0.
|
|
177
|
-
| 3 | 0.741 | 0.
|
|
178
|
-
| 4 | 0.
|
|
179
|
-
| 5 | 0.
|
|
180
|
-
| 6 | 0.
|
|
181
|
-
| 7 | 0.
|
|
182
|
-
| 8 | 0.
|
|
183
|
-
| 9 | 0.
|
|
184
|
-
| 10 | 0.
|
|
185
|
-
focus: website — coverage
|
|
175
|
+
| 1 | 0.771 | 0.775 | ★ DeepSeek-V4.1-Flash | DeepSeek | $0.37 | 75 | 1.0M | 0.277 | 0.056 | 0.138 | 0.107 | 0.197 | — |
|
|
176
|
+
| 2 | 0.744 | 0.774 | Gemini 3.8 Flash | Google | $2.91 | 95 | 1.0M | 0.271 | 0.050 | 0.144 | 0.119 | 0.189 | 1236 |
|
|
177
|
+
| 3 | 0.741 | 0.779 | ★ Muse Spark 1.3 | Meta | $3.71 | 70 | 1.0M | 0.283 | 0.053 | 0.125 | 0.103 | 0.214 | 1296 |
|
|
178
|
+
| 4 | 0.730 | 0.760 | Gemini 3.7 Flash | Google | $2.87 | 86 | 1.0M | 0.265 | 0.047 | 0.141 | 0.114 | 0.192 | 1223 |
|
|
179
|
+
| 5 | 0.727 | 0.765 | Muse Spark 1.1 | Meta | $3.71 | 127 | 1.0M | 0.269 | 0.048 | 0.148 | 0.135 | 0.165 | — |
|
|
180
|
+
| 6 | 0.725 | 0.755 | Gemini 3.6 Flash | Google | $2.87 | 132 | 1.0M | 0.244 | 0.042 | 0.140 | 0.137 | 0.190 | 1194 |
|
|
181
|
+
| 7 | 0.721 | 0.724 | ★ GLM-5.3-Flash | Zhipu AI | $0.33 | 66 | 1.0M | 0.270 | 0.047 | 0.138 | 0.101 | 0.168 | — |
|
|
182
|
+
| 8 | 0.718 | 0.788 | ★ Kimi K3 | Moonshot AI | $6.81 | 52 | 1.0M | 0.283 | 0.055 | 0.152 | 0.088 | 0.211 | 1292 |
|
|
183
|
+
| 9 | 0.702 | 0.781 | Gemini 4 Argon | Google | $7.65 | 38 | — | 0.295 | 0.057 | 0.154 | 0.070 | 0.204 | — |
|
|
184
|
+
| 10 | 0.698 | 0.709 | MiMo-V2.6-Pro | Xiaomi | $1.01 | 29 | 1.0M | 0.272 | 0.054 | 0.127 | 0.056 | 0.199 | — |
|
|
185
|
+
focus: website — coverage 127/408 (31.1%) ok; dispersion 0.992 ok; composition ok; freshness 0.0mo ok; trust unknown; modality unknown; maintenance unknown; provenance unknown; cross-source unknown
|
|
186
186
|
|
|
187
187
|
# Suggested settings.modelRoles (best-fit #1 per role, resolved via the omp catalog).
|
|
188
188
|
# Selectors are openrouter/<id>; the omp-llm-role plugin writes this block daily.
|
|
189
189
|
modelRoles:
|
|
190
190
|
default: "openrouter/deepseek/deepseek-v4.1-flash"
|
|
191
|
-
smol: "openrouter/
|
|
192
|
-
slow: "openrouter/
|
|
193
|
-
vision: "openrouter/
|
|
191
|
+
smol: "openrouter/deepseek/deepseek-v4.1-flash"
|
|
192
|
+
slow: "openrouter/google/gemini-4-argon"
|
|
193
|
+
vision: "openrouter/google/gemini-4-argon"
|
|
194
194
|
plan: "openrouter/meta/muse-spark-1.3"
|
|
195
|
-
commit: "openrouter/
|
|
195
|
+
commit: "openrouter/deepseek/deepseek-v4.1-flash"
|
|
196
196
|
tiny: "openrouter/inception/mercury-2"
|
|
197
197
|
task: "openrouter/deepseek/deepseek-v4.1-flash"
|
|
198
198
|
advisor: "openrouter/meta/muse-spark-1.3"
|