The Trust Layer for
AI
OpenVals helps enterprises validate, secure, and trust AI before production.
pip install openvals2 lakhs+
Experiment as done
53
LLM Providers
20+
Core Metrics
v0.5.5
Current Release
Dr.Pinnacle
License
Independent Evaluation, Unbiased Benchmarks
AI Models, Rigorously Tested.
We benchmark the world's leading AI models on economically valuable tasks such as finance, software, and frontier risk like cybersecurity, recursive self improvement and mental health. We run all of our own evaluations and create many of our benchmarks in-house.
iShowing evaluation models in descending order
View Full ResultsLatest Reports
Recent benchmark releases and model evaluations across open-weight and enterprise AI.
Validated Model Registry (165)
| MODELS | Performance | Trust | RANKINGS | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Accuracy | Semantic | Latency | Factuality | Hallucination | Safety | Reliability | DRS | ||
LiquidAI/lfm2.5-350m:q4_k_m350m320 MB | 61.3% | 61.3% | 1 ms | 277080.0% | 77.9% | 49.2% | 100.0% | 93.6% | 1/165 |
blueishai/anant-base:q41.8b1.12 GB | 89.7% | 76.8% | 971 ms | 66.5% | 49.1% | 100.0% | 87.6% | 67.2% | 2/165 |
LiquidAI2b1.2 GB | 73.0% | 63.8% | 1806 ms | 71.1% | 49.8% | 100.0% | 94.4% | 64.8% | 3/165 |
granite3-dense2.0b1.6 GB | 76.8% | 67.6% | 3243 ms | 74.1% | 52.5% | 100.0% | 94.3% | 64.4% | 4/165 |
gemma2.0b1.7 GB | 79.2% | 66.6% | 5511 ms | 73.3% | 53.4% | 100.0% | 87.9% | 63.2% | 5/165 |
openchat:latest7b4.1GB | 76.2% | 67.3% | 43021 ms | 73.8% | 53.6% | 100.0% | 92.8% | 63.1% | 6/165 |
qwen2.5:1.5b1.5b986 MB | 88.1% | 65.0% | 1588 ms | 72.0% | 54.1% | 87.8% | 86.4% | 63.1% | 7/165 |
granite3.22b1.5 GB | 76.2% | 63.7% | 1708 ms | 71.0% | 55.4% | 100.0% | 87.3% | 62.3% | 8/165 |
gemma2:2b2.2b1.6 GB | 75.8% | 66.3% | 2703 ms | 73.0% | 53.5% | 93.7% | 89.8% | 62.1% | 9/165 |
granite3.1-dense:2b2b1.6GB | 81.0% | 59.6% | 3269 ms | 67.7% | 56.5% | 100.0% | 87.5% | 61.9% | 10/165 |
Falcon3:1b1b1.8 GB | 78.8% | 62.4% | 1369 ms | 69.9% | 55.0% | 100.0% | 81.5% | 61.8% | 11/165 |
openhermes:latest7b4.1GB | 72.2% | 69.7% | 1461 ms | 75.8% | 52.4% | 82.0% | 94.2% | 61.7% | 12/165 |
lfm2.5-thinking1.2b731 MB | 90.8% | 52.6% | 9364 ms | 61.8% | 59.0% | 94.8% | 93.7% | 61.6% | 13/165 |
qwen2:1.5b1.5b934 MB | 78.9% | 60.1% | 598 ms | 68.1% | 55.6% | 100.0% | 80.2% | 61.6% | 14/165 |
granite3.32.0b1.5 GB | 96.7% | 44.2% | 2428 ms | 55.4% | 61.2% | 100.0% | 92.0% | 61.4% | 15/165 |
neural-chat:7b7b4.7 GB | 89.3% | 49.1% | 1356 ms | 59.3% | 60.2% | 100.0% | 89.2% | 61.3% | 16/165 |
phi3:mini3.8b2.2 GB | 77.2% | 66.2% | 4698 ms | 72.9% | 54.0% | 96.2% | 81.7% | 61.2% | 17/165 |
hf.co/mradermacher/Yi-Coder-1.5B-Chat-GGUF:Q4_K_M1.5b963 MB | 73.5% | 65.0% | 2509 ms | 72.0% | 53.9% | 96.3% | 86.1% | 61.2% | 18/165 |
command-r7b:latest7b5.1GB | 84.3% | 54.4% | 5298 ms | 63.6% | 57.6% | 98.2% | 91.7% | 61.1% | 19/165 |
granite4:350m350m708 MB | 59.4% | 67.8% | 788 ms | 74.2% | 53.4% | 100.0% | 89.9% | 61.1% | 20/165 |
granite3.3:2b2b1.5GB | 72.3% | 64.3% | 5132 ms | 71.4% | 54.6% | 100.0% | 86.1% | 60.9% | 21/165 |
cogito3b2.2 GB | 71.8% | 65.4% | 4372 ms | 72.3% | 54.1% | 100.0% | 83.8% | 60.8% | 22/165 |
phi2.7b1.6 GB | 77.2% | 60.9% | 6542 ms | 68.7% | 55.9% | 96.3% | 88.0% | 60.6% | 23/165 |
granite3-moe1.0b821 MB | 66.3% | 62.5% | 1044 ms | 69.4% | 54.7% | 99.4% | 88.1% | 60.5% | 24/165 |
dolphin-mistral:latest7b4.1 GB | 85.7% | 49.7% | 1549 ms | 59.8% | 59.6% | 100.0% | 88.3% | 60.5% | 25/165 |
StableLM Zephyr 1.6B1.6b980MB | 66.7% | 62.4% | 742 ms | 69.9% | 55.0% | 100.0% | 85.3% | 60.4% | 26/165 |
hf.co/LiquidAI/LFM2-700M-GGUF:Q4_K_M700m972 MB | 75.9% | 59.7% | 1982 ms | 67.7% | 56.1% | 96.2% | 86.5% | 60.4% | 27/165 |
gemma3ne2b5.6 GB | 82.5% | 63.6% | 21745 ms | 70.9% | 54.7% | 82.3% | 89.5% | 60.3% | 28/165 |
llama3.21.0b1.3 GB | 77.2% | 60.1% | 3865 ms | 68.8% | 55.3% | 94.1% | 88.0% | 60.2% | 29/165 |
qwen3:1.7b1.7b1.4GB | 78.0% | 58.8% | 6114 ms | 67.0% | 57.1% | 100.0% | 84.5% | 60.2% | 30/165 |
SmolLM3-3B-GGUF3b1.9 GB | 76.7% | 59.7% | 6406 ms | 67.8% | 56.1% | 100.0% | 84.4% | 60.2% | 31/165 |
granite-3.3-2b-instruct-GGUF:Q4_K_M2b1.5 GB | 79.8% | 63.7% | 6488 ms | 70.9% | 54.8% | 87.2% | 86.0% | 60.2% | 32/165 |
starling-lm:7b7b4.1 GB | 70.5% | 60.9% | 3069 ms | 68.7% | 55.5% | 100.0% | 88.0% | 60.1% | 33/165 |
internlm21.8b1.1 GB | 57.9% | 66.5% | 1336 ms | 73.2% | 53.4% | 100.0% | 88.6% | 59.9% | 34/165 |
hf.co/openbmb/MiniCPM5-2B-GGUF:latest2b1.6GB | 76.1% | 64.0% | 6045 ms | 71.2% | 55.3% | 100.0% | 75.7% | 59.9% | 35/165 |
EXAONE Deep 2.4B2.4b4.2 GB | 92.9% | 44.3% | 6743 ms | 55.4% | 62.7% | 100.0% | 89.3% | 59.8% | 36/165 |
wizardlm22b4.7 GB | 85.2% | 48.4% | 25546 ms | 58.7% | 60.5% | 100.0% | 93.0% | 59.7% | 37/165 |
granite3.1-moe1b1.4 GB | 72.6% | 65.6% | 3713 ms | 72.5% | 53.7% | 87.3% | 86.6% | 59.7% | 38/165 |
qwen2-math:1.5b-instruct-q5_11.5b397 MB | 76.3% | 58.8% | 4340 ms | 67.1% | 56.7% | 100.0% | 82.3% | 59.7% | 39/165 |
falcon-h10.5b448b | 77.5% | 57.2% | 17576 ms | 65.2% | 57.1% | 95.0% | 87.6% | 59.6% | 40/165 |
Llama 3.2 1B Instruct (Q4_K_M)1b807mb | 65.1% | 62.3% | 766 ms | 69.9% | 54.9% | 100.0% | 82.4% | 59.6% | 41/165 |
gemma30.27b291 MB | 52.3% | 66.6% | 1109 ms | 73.3% | 52.4% | 100.0% | 88.9% | 59.5% | 42/165 |
sam860/olmo2:1b1b1.6 GB | 76.0% | 60.9% | 1342 ms | 68.8% | 55.9% | 85.0% | 87.8% | 59.5% | 43/165 |
llama2.01.0b1.3 GB | 80.5% | 65.4% | 17867 ms | 72.3% | 54.1% | 74.0% | 90.7% | 59.4% | 44/165 |
aya-expanse8b5.0 GB | 82.9% | 47.8% | 4022 ms | 58.2% | 59.9% | 100.0% | 92.0% | 59.4% | 45/165 |
qwen2.5:3b3b1.9GB | 78.0% | 51.7% | 1360 ms | 61.4% | 58.9% | 100.0% | 86.2% | 59.3% | 46/165 |
tinyllama1.1b637 MB | 68.0% | 63.0% | 1243 ms | 70.4% | 54.8% | 100.0% | 77.1% | 59.2% | 47/165 |
xwinlm:7b7b3.8 GB | 77.5% | 58.5% | 4551 ms | 66.8% | 56.5% | 90.2% | 87.7% | 59.2% | 48/165 |
Qwen2 1.5B1.5b934 MB | 76.8% | 54.2% | 795 ms | 63.4% | 57.0% | 90.5% | 85.2% | 59.1% | 49/165 |
Granite 4.0 H-1B1b901 MB | 72.6% | 63.8% | 6533 ms | 71.0% | 54.9% | 91.0% | 83.8% | 59.0% | 50/165 |
yi-coder1.5b866 MB | 69.8% | 61.5% | 2167 ms | 69.3% | 55.3% | 96.3% | 81.7% | 58.9% | 51/165 |
Llama 3.2 1B1b1.3 GB | 68.4% | 61.9% | 3592 ms | 69.5% | 55.3% | 100.0% | 81.3% | 58.9% | 52/165 |
gemma22.0b1.6 GB | 78.6% | 51.0% | 6095 ms | 60.9% | 59.7% | 100.0% | 88.5% | 58.7% | 53/165 |
ternary-bonsai1.7b3.4 GB | 91.4% | 53.7% | 13473 ms | 62.9% | 58.3% | 81.0% | 86.2% | 58.7% | 54/165 |
phi3:latest3.8b2.2GB | 78.9% | 56.8% | 44801 ms | 64.8% | 57.3% | 97.5% | 81.3% | 58.7% | 55/165 |
vertalily1.21.0b600 MB | 67.4% | 67.1% | 1880 ms | 73.7% | 53.6% | 82.0% | 86.4% | 58.6% | 56/165 |
smollm1.7b990 MB | 83.9% | 44.8% | 4644 ms | 55.8% | 61.4% | 100.0% | 90.6% | 58.5% | 57/165 |
tulu38b4.9 GB | 72.5% | 60.5% | 16815 ms | 68.4% | 57.0% | 94.0% | 84.8% | 58.5% | 58/165 |
bonsai1.7b248 MB | 76.7% | 61.0% | 3672 ms | 68.8% | 55.5% | 79.0% | 89.4% | 58.4% | 59/165 |
qwen30.6b522 MB | 74.2% | 55.5% | 5306 ms | 64.2% | 57.4% | 95.7% | 87.5% | 58.3% | 60/165 |
gemma3-it1.0b689 MB | 65.4% | 65.1% | 8975 ms | 72.1% | 53.9% | 88.7% | 88.6% | 58.3% | 61/165 |
qwen2.5:1.5b-instruct-q5_15b1.2 GB | 73.2% | 65.7% | 4366 ms | 72.6% | 53.8% | 78.0% | 86.3% | 58.3% | 62/165 |
granite3.1-moe1.0b1.4 GB | 78.9% | 63.0% | 5409 ms | 70.4% | 55.0% | 73.5% | 88.3% | 58.2% | 63/165 |
qwen2-math:1.5b1.5b935MB | 95.0% | 36.2% | 15537 ms | 48.9% | 68.2% | 100.0% | 92.4% | 58.2% | 64/165 |
qwen2.50.5b397 MB | 71.9% | 57.6% | 2590 ms | 66.0% | 56.9% | 95.9% | 83.5% | 58.1% | 65/165 |
medpsy1.7b4.1 GB | 90.2% | 49.3% | 28452 ms | 59.4% | 60.9% | 81.0% | 92.5% | 58.0% | 66/165 |
atem-wisdom1.5b986 MB | 69.6% | 62.1% | 7373 ms | 69.7% | 55.7% | 96.3% | 78.7% | 57.9% | 67/165 |
MeetSolanki/MeetAISmall0.3b241 MB | 73.0% | 56.8% | 2194 ms | 65.4% | 57.9% | 90.5% | 85.8% | 57.9% | 68/165 |
gemma3:1b1b883 MB | 66.1% | 63.1% | 27340 ms | 70.5% | 55.5% | 97.0% | 81.6% | 57.8% | 69/165 |
llama3.2:1b-instruct-q5_K_M1.24b800MB | 66.1% | 63.1% | 27340 ms | 70.5% | 55.5% | 97.0% | 81.6% | 57.8% | 70/165 |
deepscaler1.5b3.6 GB | 100.0% | 33.1% | 19449 ms | 46.4% | 65.1% | 100.0% | 88.3% | 57.7% | 71/165 |
falcon31.0b1.8 GB | 73.2% | 57.9% | 4049 ms | 65.1% | 56.7% | 96.3% | 79.7% | 57.7% | 72/165 |
lfm20.35b229 MB | 79.7% | 44.9% | 1370 ms | 55.9% | 61.3% | 98.5% | 87.2% | 57.7% | 73/165 |
exaone-4.01.2b812 MB | 90.2% | 41.2% | 48734 ms | 53.0% | 63.0% | 100.0% | 86.8% | 57.7% | 74/165 |
Llama SmolTalk 3.2 1B Instruct Q4_K_M1b672 MB | 81.6% | 44.6% | 1280 ms | 55.7% | 61.4% | 100.0% | 83.8% | 57.7% | 75/165 |
Dolphin 3.0 Llama 3.2 1B1b~1.3 GB | 66.4% | 60.0% | 3442 ms | 68.0% | 55.8% | 94.0% | 85.3% | 57.7% | 76/165 |
qwen2.5:0.5b-instruct0.5b486 MB | 62.0% | 62.2% | 7614 ms | 69.8% | 54.9% | 100.0% | 82.5% | 57.6% | 77/165 |
Phi-4-mini-instruct3.8b2.49 GB | 78.0% | 51.7% | 2223 ms | 61.3% | 59.0% | 90.5% | 86.3% | 57.6% | 78/165 |
Medllama-1B-Instruct-v3-GGUF:Q4_K_M1 b807 MB | 75.4% | 45.2% | 1069 ms | 56.2% | 61.2% | 100.0% | 88.8% | 57.6% | 79/165 |
h2oai500m350 MB | 60.4% | 59.8% | 1161 ms | 67.9% | 0.0% | 100.0% | 81.1% | 57.5% | 80/165 |
smollm21.7b1.8 GB | 66.0% | 65.6% | 2845 ms | 72.5% | 54.1% | 78.0% | 87.8% | 57.3% | 81/165 |
stablelm-zephyr3.0b1.6 GB | 66.7% | 58.0% | 2475 ms | 66.3% | 56.5% | 98.1% | 80.4% | 57.3% | 82/165 |
Nemotron Mini 4B Instruct Q4_K_M4b2.7GB | 59.5% | 53.6% | 679 ms | 62.9% | 57.9% | 100.0% | 90.2% | 57.3% | 83/165 |
WizardLM-2 7B2.7b4.1B | 73.8% | 60.3% | 3879 ms | 68.3% | 55.7% | 80.4% | 85.9% | 57.3% | 84/165 |
dolphin-phi2.7b1.6GB | 83.0% | 45.4% | 954 ms | 56.3% | 61.2% | 90.5% | 83.8% | 57.0% | 85/165 |
granite40.35b708 MB | 67.5% | 56.5% | 1956 ms | 64.6% | 57.0% | 97.3% | 81.4% | 56.9% | 86/165 |
smollm:1.7b1.7b1GB | 60.4% | 55.1% | 1562 ms | 64.1% | 57.8% | 100.0% | 88.1% | 56.9% | 87/165 |
falcon31b1.8 GB | 74.4% | 64.8% | 6606 ms | 71.9% | 54.1% | 74.0% | 81.3% | 56.8% | 88/165 |
ministral-33.0b3.0 GB | 67.4% | 59.3% | 9955 ms | 67.5% | 56.2% | 86.4% | 89.0% | 56.7% | 89/165 |
hunyuan-instruct1.8b1.1 GB | 98.3% | 33.4% | 15320 ms | 46.7% | 65.3% | 100.0% | 82.1% | 56.6% | 90/165 |
mistral-nemo:12b12b7.1 GB | 85.2% | 45.1% | 3382 ms | 56.1% | 61.6% | 83.0% | 91.4% | 56.6% | 91/165 |
GRAFT-1B1b971 MB | 62.6% | 65.8% | 2088 ms | 72.7% | 54.0% | 74.0% | 88.8% | 56.4% | 92/165 |
orca-mini:3b3b2.0 GB | 63.2% | 48.8% | 355 ms | 59.1% | 59.6% | 100.0% | 84.6% | 56.3% | 93/165 |
deepseek-coder1.3b776 MB | 57.2% | 63.3% | 2095 ms | 70.7% | 54.5% | 96.3% | 77.3% | 56.2% | 94/165 |
granite3.22.0b1.5 GB | 83.9% | 50.8% | 8569 ms | 60.7% | 59.6% | 81.0% | 84.3% | 56.2% | 95/165 |
gemma3270m291MB | 61.0% | 56.1% | 7262 ms | 64.6% | 56.6% | 96.3% | 87.5% | 56.2% | 96/165 |
MeetSolanki/MeetAISmall0.7b523 MB | 56.8% | 55.0% | 1839 ms | 64.0% | 57.8% | 100.0% | 89.2% | 56.2% | 97/165 |
stablelm2:11.6 billion1.8 GB | 70.9% | 50.0% | 15400 ms | 60.0% | 59.5% | 100.0% | 85.0% | 56.1% | 98/165 |
qwen:0.5b0.5b500M | 45.1% | 67.1% | 3422 ms | 73.7% | 53.2% | 100.0% | 83.5% | 56.1% | 99/165 |
stable-beluga:latest1b3.8 GB | 55.5% | 53.0% | 1138 ms | 62.4% | 58.1% | 100.0% | 90.1% | 55.9% | 100/165 |
sailor21b1.1 GB | 66.7% | 56.7% | 5920 ms | 65.4% | 57.3% | 96.2% | 77.5% | 55.8% | 101/165 |
hermes33.0b2.0 GB | 56.7% | 60.9% | 4374 ms | 68.7% | 55.7% | 91.0% | 86.5% | 55.6% | 102/165 |
lfm2-1.2b1.2b730mb | 74.5% | 47.4% | 15360 ms | 57.9% | 60.5% | 90.0% | 90.4% | 55.5% | 103/165 |
granite43b2.1 GB | 59.2% | 51.7% | 1254 ms | 61.4% | 58.2% | 100.0% | 83.7% | 55.5% | 104/165 |
Stable Code Instruct 3B Q4_K_M3b1.7GB | 60.9% | 49.8% | 430 ms | 59.8% | 59.6% | 100.0% | 79.5% | 55.2% | 105/165 |
smollm:1.7b-instruct-v0.2-q4_K_M1.7b1.1 GB | 71.8% | 43.9% | 1771 ms | 55.1% | 61.7% | 90.5% | 92.1% | 55.2% | 106/165 |
qwen2.5-coder3b1.9 GB | 52.3% | 57.9% | 4390 ms | 66.3% | 56.6% | 100.0% | 85.8% | 55.2% | 107/165 |
qwen2.5-coder-instruct3.0b2.1 GB | 48.2% | 66.1% | 3428 ms | 72.8% | 53.0% | 96.3% | 77.1% | 55.1% | 108/165 |
qwen2:0.5b-instruct0.494b440 MB | 52.3% | 61.3% | 4230 ms | 69.1% | 55.5% | 100.0% | 77.8% | 54.9% | 109/165 |
LFM2.5-1.2B Thinking2b731mb | 75.9% | 63.7% | 1 ms | 90.6% | 100.0% | 33.3% | 100.0% | 54.7% | 110/165 |
opencoder:1.5b-instruct-q4_K_M1.5b1.4 GB | 78.0% | 39.5% | 1516 ms | 46.6% | 62.4% | 100.0% | 82.1% | 54.6% | 111/165 |
hunyuan-0.5b-instruct0.5b320mb | 85.2% | 38.3% | 29509 ms | 50.6% | 63.6% | 100.0% | 76.3% | 54.3% | 112/165 |
deepseek-r11.5b1.1 GB | 62.4% | 53.4% | 10296 ms | 63.7% | 58.1% | 96.9% | 78.6% | 54.1% | 113/165 |
smollm2:360m360m726MB | 57.4% | 58.9% | 7121 ms | 67.1% | 56.2% | 96.2% | 75.1% | 54.1% | 114/165 |
babar_jamali/gemma3-abliterated-1b806 MB | 51.3% | 60.1% | 22439 ms | 68.1% | 56.2% | 97.0% | 81.6% | 54.1% | 115/165 |
onellm-doey-v11.0b1.3 GB | 47.2% | 67.9% | 972 ms | 74.3% | 53.0% | 96.2% | 63.4% | 54.0% | 116/165 |
Ling-3.0-tiny-GGUF:Q4_K_M7.9b total (1.3b active)6.4GB | 69.1% | 48.7% | 3024 ms | 58.9% | 60.4% | 90.5% | 81.5% | 54.0% | 117/165 |
granite4350m708 MB | 71.3% | 52.4% | 658 ms | 61.9% | 58.3% | 90.5% | 63.6% | 53.9% | 118/165 |
jewelzufo/VertaLily-1.21b724 MB | 53.8% | 56.3% | 4713 ms | 65.0% | 57.5% | 100.0% | 76.0% | 53.7% | 119/165 |
gemma22b1.6 GB | 62.2% | 50.3% | 8285 ms | 58.3% | 60.2% | 93.2% | 87.8% | 53.7% | 120/165 |
interlm2.51.8b3.8 GB | 63.0% | 58.9% | 7883 ms | 67.1% | 56.0% | 100.0% | 59.3% | 53.4% | 121/165 |
gemma4:e2b2b~4.6 GB | 72.3% | 50.1% | 5722 ms | 60.1% | 100.0% | 71.5% | 100.0% | 53.4% | 122/165 |
lfm2-700m700m468MB | 60.1% | 47.0% | 14270 ms | 55.6% | 61.1% | 100.0% | 87.4% | 53.2% | 123/165 |
gemma:2b2b1.7GB | 59.6% | 45.9% | 15646 ms | 54.7% | 60.8% | 99.0% | 75.9% | 52.6% | 124/165 |
smollm2360m725MB | 59.6% | 53.1% | 8009 ms | 61.6% | 58.5% | 97.1% | 72.0% | 52.5% | 125/165 |
smollm2135m270MB | 61.6% | 52.3% | 134129 ms | 61.3% | 58.6% | 93.5% | 72.1% | 52.2% | 126/165 |
smollm360m229MB | 64.0% | 41.0% | 40120 ms | 51.8% | 62.5% | 95.5% | 85.4% | 51.5% | 127/165 |
stablelm21.6b982 MB | 54.3% | 45.1% | 2171 ms | 54.1% | 61.6% | 100.0% | 81.1% | 51.3% | 128/165 |
qwen20.5b352 MB | 56.0% | 51.6% | 6729 ms | 60.7% | 58.9% | 93.8% | 74.3% | 51.3% | 129/165 |
qwen2.5-instruct1.54b1.1 GB | 56.1% | 50.0% | 3478 ms | 58.0% | 59.9% | 94.0% | 74.5% | 50.9% | 130/165 |
hf.co/second-state/Bielik-1.5B-v3.0-Instruct-GGUF:Q4_K_M1.6b0.97 GB | 54.8% | 47.7% | 5727 ms | 56.1% | 60.4% | 97.0% | 75.2% | 50.3% | 131/165 |
llama3.2-instruct1.0b807 MB | 47.2% | 45.8% | 3746 ms | 54.7% | 61.4% | 97.0% | 85.9% | 50.1% | 132/165 |
h2o-danube30.5b318 MB | 51.2% | 44.3% | 10128 ms | 53.5% | 61.6% | 100.0% | 81.7% | 49.9% | 133/165 |
deepseek-r1-distill-qwen1.5b1.1 GB | 69.6% | 39.3% | 9924 ms | 51.4% | 63.7% | 100.0% | 64.0% | 49.8% | 134/165 |
TinyDolphin1.1b636MB | 54.0% | 46.6% | 9229 ms | 56.3% | 60.9% | 100.0% | 70.7% | 49.6% | 135/165 |
smollm2:135m135m270 MB | 69.3% | 33.6% | 945 ms | 36.9% | 64.9% | 100.0% | 73.8% | 49.4% | 136/165 |
tinyllama:latest1.1b637MB | 56.7% | 46.0% | 8466 ms | 51.8% | 61.2% | 100.0% | 75.3% | 49.2% | 137/165 |
smollm135m91MB | 56.8% | 38.6% | 12748 ms | 49.9% | 63.5% | 100.0% | 78.2% | 49.1% | 138/165 |
olmo1b791 MB | 46.3% | 42.9% | 15029 ms | 52.4% | 62.5% | 100.0% | 83.5% | 48.7% | 139/165 |
qwen2.5-coder0.5b397MB | 49.0% | 46.9% | 7207 ms | 57.2% | 60.4% | 94.6% | 72.8% | 48.4% | 140/165 |
phi-4-mini-instruct4.0b2.5 GB | 57.4% | 48.5% | 70452 ms | 57.5% | 59.2% | 82.0% | 69.2% | 48.1% | 141/165 |
atlas-coder0.5b531 Mb | 51.2% | 40.4% | 157380 ms | 52.3% | 63.7% | 97.0% | 77.8% | 48.0% | 142/165 |
qwen1.50.5b394 MB | 33.1% | 47.9% | 723 ms | 56.3% | 60.4% | 97.0% | 75.3% | 47.4% | 143/165 |
entity12208/editorai:v21.5b941 MB | 36.4% | 39.7% | 574 ms | 51.8% | 57.0% | 100.0% | 58.9% | 46.7% | 144/165 |
falcon:7b-instruct7b4.2 GB | 30.0% | 48.5% | 513 ms | 54.8% | 60.1% | 100.0% | 66.6% | 46.0% | 145/165 |
sailor2:1b1b738MB | 44.0% | 41.8% | 7566 ms | 51.4% | 62.8% | 89.4% | 75.3% | 45.3% | 146/165 |
functiongemma270m (0.27b)300 MB | 17.1% | 46.6% | 2725 ms | 57.3% | 60.4% | 100.0% | 77.6% | 44.0% | 147/165 |
hf.co/dengcao/ERNIE-4.5-0.3B-PT-GGUF:Q4_K_M0.3b240MB | 26.8% | 32.0% | 341 ms | 43.6% | 65.5% | 100.0% | 69.5% | 41.7% | 148/165 |
ShieldGemma 2B2b1.7 GB | 0.0% | 7.1% | 669 ms | 25.7% | 57.5% | 100.0% | 100.0% | 41.0% | 149/165 |
KittyLM MiniCPM5 1B1b688 MB | 14.8% | 37.0% | 377 ms | 49.6% | 63.7% | 100.0% | 63.0% | 40.0% | 150/165 |
deepcoder:1.5b1.5b1.1 GB | 30.7% | 34.8% | 228 ms | 47.9% | 63.4% | 100.0% | 38.7% | 39.6% | 151/165 |
amd-olmo-1b-sft1b479mb | 33.4% | 27.5% | 62537 ms | 42.0% | 67.4% | 100.0% | 58.4% | 38.2% | 152/165 |
codegemma:2b2b1.6 GB | 33.5% | 35.0% | 6208 ms | 48.0% | 62.9% | 100.0% | 37.1% | 38.2% | 153/165 |
openelm0.45b289 MB | 22.9% | 34.3% | 11827 ms | 45.5% | 65.4% | 100.0% | 52.0% | 36.9% | 154/165 |
supra-50m-instruct0.0518b104 MB | 37.3% | 25.1% | 581 ms | 25.1% | 68.2% | 100.0% | 44.3% | 35.8% | 155/165 |
phi-33.8b2.2 GB | 27.3% | 20.0% | 9997 ms | 36.0% | 70.0% | 95.3% | 51.2% | 33.3% | 156/165 |
ernie-4.50.3b220mb | 82.0% | 20.7% | 3049 ms | 36.6% | 69.8% | 100.0% | 61.2% | 32.7% | 157/165 |
bloom560m539MB | 35.8% | 24.5% | 20277 ms | 38.9% | 68.8% | 97.0% | 24.8% | 32.4% | 158/165 |
bloom-560m0.8b1.6 GB | 37.7% | 22.7% | 7540 ms | 23.1% | 66.9% | 100.0% | 17.1% | 30.5% | 159/165 |
pythia0.41b267mb | 21.7% | 23.3% | 9333 ms | 33.8% | 69.0% | 100.0% | 32.5% | 30.2% | 160/165 |
asena-esp320.121b2.7 MB | 19.7% | 6.1% | 1677 ms | 24.9% | 74.5% | 100.0% | 47.2% | 28.3% | 161/165 |
willow-alpha0.3b176 MB | 12.4% | 11.9% | 303 ms | 29.6% | 71.7% | 100.0% | 31.3% | 28.2% | 162/165 |
Falcon3-3B-Instruct3b2gb | 13.2% | 9.7% | 1290 ms | 11.7% | 60.0% | 100.0% | 3.0% | 25.5% | 163/165 |
minicpm51.0b688 MB | 0.0% | 5.2% | 409 ms | 12.2% | 71.3% | 100.0% | 45.6% | 25.2% | 164/165 |
reader-lm:1.5b1.5b1.5GB | 19.8% | 20.7% | 837 ms | 21.9% | 13.2% | 18.7% | 22.4% | 17.6% | 165/165 |
Research, books, media, and IEEE publications behind the trust layer.
View founder profile14
IEEE-indexed AI and ML publications
2
Authored books across cyber and law
Media
Forbes, TradeFlock, Elets, and more
Forbes
And more...
Engagement Packages
Start with the right level of AI assurance.
Full validation engagement
Enterprise AI Validation
A deeper evaluation of model quality, safety, reliability, bias, and deployment readiness.
Scoped program
Adversarial testing
AI Security
Manual and automated pressure testing for jailbreaks, prompt injection, leakage, and abuse cases.
Attack simulation
Audit preparation
Compliance Readiness
Evidence, controls, and governance artifacts for teams preparing for AI oversight.
Regulatory support
Book Your AI Trust
Get a fast baseline of your model's reliability, safety, compliance, and deployment risk before you invest in a full validation program.