← 返回 API Dashboard

本机回环 API · 本页为 registry 静态快照

Free Model Chain — 模型分数全览

展示全部免费模型的分层评分与 routing_score 加权计算过程。数据来自 model-registry-latest.json，非实时调用 8022 API。API 仍仅本机 127.0.0.1:8022 可访问。

更新时间
2026-10-09 18:10:47 CST
scoring_version
v3-routing
quality 覆盖
10 / 19 模型已 quality 评测（0.5263）
数据来源
reports/run-20260606-011232/benchmark.json + current OpenRouter free catalog filter + quality benchmarks merged + newer partial gate runs merged

general 推荐链（按 routing 排序）

  1. nvidia/nemotron-3-ultra-550b-a55b:free
  2. nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  3. poolside/laguna-s-2.1:free
  4. google/gemma-4-26b-a4b-it:free
  5. openrouter/free

buildsignal 推荐链

  1. nvidia/nemotron-3-ultra-550b-a55b:free
  2. nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
  3. poolside/laguna-s-2.1:free
  4. google/gemma-4-26b-a4b-it:free
  5. openrouter/free
#1

nvidia/nemotron-3-ultra-550b-a55b:free

0.9414 routing_score 推荐

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.9530 ×0.45 0.4289
gate_score 1.0000 ×0.20 0.2000
stability_score 0.9000 ×0.20 0.1800
format_score 1.0000 ×0.10 0.1000
latency_score (13729 ms) 0.6500 ×0.05 0.0325
合计 → routing_score 0.9414

② Gate 层（smoke test）

gate_score = 1.0000（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段1.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.9530
effective_quality_score0.9530
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.9900
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 13729
  • BuildSignal recommended: 推荐
#2

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

0.9410 routing_score 推荐

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.9299 ×0.45 0.4185
gate_score 1.0000 ×0.20 0.2000
stability_score 0.9000 ×0.20 0.1800
format_score 1.0000 ×0.10 0.1000
latency_score (7657 ms) 0.8500 ×0.05 0.0425
合计 → routing_score 0.9410

② Gate 层（smoke test）

gate_score = 1.0000（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段1.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.9299
effective_quality_score0.9299
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.7160
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 7657
  • BuildSignal recommended: 推荐
#3

poolside/laguna-s-2.1:free

0.8222 routing_score 推荐

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.9161 ×0.45 0.4122
gate_score 1.0000 ×0.20 0.2000
stability_score 0.3000 ×0.20 0.0600
format_score 1.0000 ×0.10 0.1000
latency_score (4349 ms) 1.0000 ×0.05 0.0500
合计 → routing_score 0.8222

② Gate 层（smoke test）

gate_score = 1.0000（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段1.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.9161
effective_quality_score0.9161
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.8387
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 4349
  • BuildSignal recommended: 推荐
#4

google/gemma-4-26b-a4b-it:free

0.8110 routing_score 推荐

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.9600 ×0.45 0.4320
gate_score 0.9375 ×0.20 0.1875
stability_score 0.3000 ×0.20 0.0600
format_score 0.9900 ×0.10 0.0990
latency_score (11762 ms) 0.6500 ×0.05 0.0325
合计 → routing_score 0.8110

② Gate 层（smoke test）

gate_score = 0.9375（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段0.7500

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.9600
effective_quality_score0.9600
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.9500
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 11762
  • BuildSignal recommended: 推荐
#5

openrouter/free

0.7504 routing_score 推荐

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.8480 ×0.45 0.3816
gate_score 0.9375 ×0.20 0.1875
stability_score 0.3000 ×0.20 0.0600
format_score 0.8880 ×0.10 0.0888
latency_score (15945 ms) 0.6500 ×0.05 0.0325
合计 → routing_score 0.7504

② Gate 层（smoke test）

gate_score = 0.9375（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段0.7500

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.8480
effective_quality_score0.8480
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.4400
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 15945
  • BuildSignal recommended: 推荐
#6

google/gemma-4-31b-it:free

0.7265 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.9867 ×0.45 0.4440
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 1.0000 ×0.10 0.1000
latency_score (8363 ms) 0.8500 ×0.05 0.0425
合计 → routing_score 0.7265

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.9867
effective_quality_score0.9867
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 1.0000
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 8363
  • BuildSignal recommended: —
#7

nvidia/nemotron-3-super-120b-a12b:free

0.6966 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.8063 ×0.45 0.3628
gate_score 0.8750 ×0.20 0.1750
stability_score 0.3000 ×0.20 0.0600
format_score 0.7880 ×0.10 0.0788
latency_score (47176 ms) 0.4000 ×0.05 0.0200
合计 → routing_score 0.6966

② Gate 层（smoke test）

gate_score = 0.8750（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段0.5000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.8063
effective_quality_score0.8063
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.4400
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 47176
  • BuildSignal recommended: —
#8

inclusionai/ling-3.1-flash

0.6856 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.7681 ×0.45 0.3456
gate_score 0.7500 ×0.20 0.1500
stability_score 0.3000 ×0.20 0.0600
format_score 0.8750 ×0.10 0.0875
latency_score (5869 ms) 0.8500 ×0.05 0.0425
合计 → routing_score 0.6856

② Gate 层（smoke test）

gate_score = 0.7500（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段0.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.7681
effective_quality_score0.7681
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.8240
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 5869
  • BuildSignal recommended: —
#9

cohere/north-mini-code:free

0.6718 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.5703 ×0.45 0.2566
gate_score 1.0000 ×0.20 0.2000
stability_score 0.7000 ×0.20 0.1400
format_score 0.5520 ×0.10 0.0552
latency_score (28583 ms) 0.4000 ×0.05 0.0200
合计 → routing_score 0.6718

② Gate 层（smoke test）

gate_score = 1.0000（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning1.0000
BuildSignal 片段1.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.5703
effective_quality_score0.5703
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.2600
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 28583
  • BuildSignal recommended: —
#10

liquid/lfm-2.5-2.6b:free

0.6619 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.5875 ×0.45 0.2644
gate_score 0.6875 ×0.20 0.1375
stability_score 0.7000 ×0.20 0.1400
format_score 1.0000 ×0.10 0.1000
latency_score (40889 ms) 0.4000 ×0.05 0.0200
合计 → routing_score 0.6619

② Gate 层（smoke test）

gate_score = 0.6875（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct1.0000
简单推理 reasoning0.0000
BuildSignal 片段0.7500

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.6875 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.6875
effective_quality_score0.5875
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 40889
  • BuildSignal recommended: —
#11

nvidia/nemotron-3.5-lightning:free

0.5763 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.5250 ×0.45 0.2363
gate_score 0.6250 ×0.20 0.1250
stability_score 0.7000 ×0.20 0.1400
format_score 0.2500 ×0.10 0.0250
latency_score (4688 ms) 1.0000 ×0.05 0.0500
合计 → routing_score 0.5763

② Gate 层（smoke test）

gate_score = 0.6250（四题通过率均值）

中文 zh_summary0.5000
JSON json_struct0.0000
简单推理 reasoning1.0000
BuildSignal 片段1.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.6250 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.6250
effective_quality_score0.5250
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 4688
  • BuildSignal recommended: —
#12

dots-studio/dots-3-note-preview:free

0.5200 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.4000 ×0.45 0.1800
gate_score 0.5000 ×0.20 0.1000
stability_score 0.7000 ×0.20 0.1400
format_score 0.5000 ×0.10 0.0500
latency_score (2901 ms) 1.0000 ×0.05 0.0500
合计 → routing_score 0.5200

② Gate 层（smoke test）

gate_score = 0.5000（四题通过率均值）

中文 zh_summary1.0000
JSON json_struct0.0000
简单推理 reasoning1.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.5000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.5000
effective_quality_score0.4000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)1.0000 = gate 推理

④ 其它

  • latency_ms: 2901
  • BuildSignal recommended: —
#13

nvidia/nemotron-3.5-content-safety:free

0.3398 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.2270 ×0.45 0.1022
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.5520 ×0.10 0.0552
latency_score (6491 ms) 0.8500 ×0.05 0.0425
合计 → routing_score 0.3399

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

quality_score 来自五大能力类等权平均；Reasoning 类内部由 5 道题平均（见仓库 data/README.md）。

quality_score0.2270
effective_quality_score0.2270
quality_score_sourcequality_benchmark
quality_penalty0.0000
quality_evaluated是
quality_reasoning（多约束推理）: 0.2600
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 6491
  • BuildSignal recommended: —
#14

poolside/laguna-xs-2.1:free

0.2263 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0250 ×0.45 0.0113
gate_score 0.1250 ×0.20 0.0250
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (1041 ms) 1.0000 ×0.05 0.0500
合计 → routing_score 0.2263

② Gate 层（smoke test）

gate_score = 0.1250（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.5000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.1250 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.1250
effective_quality_score0.0250
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.5000 = gate 推理

④ 其它

  • latency_ms: 1041
  • BuildSignal recommended: —
#15

apodex/apodex-1.1-mini:free

0.1900 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0000 ×0.45 0.0000
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (3343 ms) 1.0000 ×0.05 0.0500
合计 → routing_score 0.1900

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.0000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.0000
effective_quality_score0.0000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 3343
  • BuildSignal recommended: —
#16

google/lyria-3-clip-preview

0.1400 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0000 ×0.45 0.0000
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (0 ms) 0.0000 ×0.05 0.0000
合计 → routing_score 0.1400

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.0000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.0000
effective_quality_score0.0000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 0
  • BuildSignal recommended: —
#17

google/lyria-3-pro-preview

0.1400 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0000 ×0.45 0.0000
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (0 ms) 0.0000 ×0.05 0.0000
合计 → routing_score 0.1400

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.0000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.0000
effective_quality_score0.0000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 0
  • BuildSignal recommended: —
#18

thinkingmachines/inkling-small:free

0.1400 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0000 ×0.45 0.0000
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (0 ms) 0.0000 ×0.05 0.0000
合计 → routing_score 0.1400

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.0000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.0000
effective_quality_score0.0000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 0
  • BuildSignal recommended: —
#19

thinkingmachines/inkling:free

0.1400 routing_score —

① 最终分 routing_score 计算

routing = effective_quality×0.45 + gate×0.20 + stability×0.20 + format×0.10 + latency_score×0.05

项原始分×权重加权贡献
effective_quality_score 0.0000 ×0.45 0.0000
gate_score 0.0000 ×0.20 0.0000
stability_score 0.7000 ×0.20 0.1400
format_score 0.0000 ×0.10 0.0000
latency_score (0 ms) 0.0000 ×0.05 0.0000
合计 → routing_score 0.1400

② Gate 层（smoke test）

gate_score = 0.0000（四题通过率均值）

中文 zh_summary0.0000
JSON json_struct0.0000
简单推理 reasoning0.0000
BuildSignal 片段0.0000

③ Quality 层

未跑 quality benchmark：quality_score 为 gate 兜底；effective = gate − penalty (0.0000 − 0.1000)。quality_score_missing; used gate_score as fallback

quality_score0.0000
effective_quality_score0.0000
quality_score_sourcegate_fallback
quality_penalty0.1000
quality_evaluated否
quality_reasoning: 未评测
reasoning_score (legacy)0.0000 = gate 推理

④ 其它

  • latency_ms: 0
  • BuildSignal recommended: —

评分细则见仓库 00-projects/22-openrouter-free-benchmark/data/README.md。本页随 build_model_registry.py 自动刷新。