Best model for knowledge & honesty
Models ranked by their knowledge & honesty score, 0 to 100, as on the category page. Only ranked models with enough scored items are included, and models are grouped by total parameters.
Read the memory figure as an estimate, not a guarantee. The memory a model needs is estimated from its file: the weights plus about 20% for the context of a single conversation. It is not a measurement, and a long conversation or several at once needs more. A model with no file size on record is not counted as fitting any amount of memory. Speeds, and the GPU memory shown on the speed page, were measured on this benchmark's server, not on yours. That server kept 1 to 8 answers in flight at a time and loaded a context window of 16,384 tokens for most models; 42 of the models ranked ran at a shorter context. Speeds were measured on one laptop and are comparable only between models on the same backend. See the settings and the memory method.
All sizes
Aya Expanse 32B leads here with 100.0 on a scale of 0 to 100; its Overall is 78.8 (95% interval 74.6–82.9).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | Aya Expanse 32B | 100.030 of 30 items scored | 78.874.6–82.9 | 72–137 | 10.0ROCm 7.1 | 23.8 | 16–35B |
| 1 | Deepcoder 14B Previewfine-tune of DeepSeek-R1-Distill-Qwen 14Bcode model | 100.030 of 30 items scored | 74.569.5–79.0 | 84–146 | 6.7ROCm 7.1 | 10.8 | 9–16B |
| 1 | DeepSeek-R1-Distill-Qwen-14B | 100.030 of 30 items scored | 85.381.2–89.2 | 38–106 | 7.1ROCm 7.1 | 10.8 | 9–16B |
| 1 | DeepSeek-R1-Distill-Qwen-32B | 100.030 of 30 items scored | 89.186.0–91.9 | 19–85 | 3.1ROCm 7.1 | 23.8 | 16–35B |
| 1 | Devstral 24B Small 2505code model | 100.030 of 30 items scored | 88.985.6–92.0 | 23–86 | 4.2ROCm 7.1 | 17.2 | 16–35B |
Tiny (under 3B)
Qwen2.5 1.5B Instruct leads its size class with 93.3 on a scale of 0 to 100; its Overall is 68.5 (95% interval 63.2–73.7).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5 1.5B Instruct | 93.330 of 30 items scored | 68.563.2–73.7 | 111–160 | 45.5ROCm 7.1 | 1.2 | Tiny (under 3B) |
| 1 | Qwen3 VL 2B Instruct | 93.330 of 30 items scored | 77.472.5–82.1 | 68–137 | 26.5ROCm 7.1 | 2.3 | Tiny (under 3B) |
| 3 | Exaone3.5 2.4B Instruct | 90.030 of 30 items scored | 76.370.9–81.3 | 73–141 | 100.9ROCm 7.1 | 1.9 | Tiny (under 3B) |
| 3 | Granite3.3 2B | 90.030 of 30 items scored | 68.663.8–73.8 | 111–159 | 28.6ROCm 7.1 | 1.8 | Tiny (under 3B) |
| 3 | Lfm3 1.7B | 90.030 of 30 items scored | 70.265.3–75.3 | 96–162 | 42.1ROCm 7.1 | 1.3 | Tiny (under 3B) |
3–4B
Qwen2.5-VL-3B-Instruct leads its size class with 100.0 on a scale of 0 to 100; its Overall is 72.3 (95% interval 67.2–77.6).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5-VL-3B-Instruct | 100.030 of 30 items scored | 72.367.2–77.6 | 90–157 | 21.9ROCm 7.1 | 3.8 | 3–4B |
| 2 | Phi-3-mini-4k-instruct | 96.730 of 30 items scored | 63.458.3–68.1 | 129–182 | 17.6ROCm 7.1 | 2.9 | 3–4B |
| 2 | Phi-4-mini-instruct | 96.730 of 30 items scored | 81.677.1–86.0 | 62–123 | 17.1ROCm 7.1 | 3.0 | 3–4B |
| 2 | Phi3 3.8B Mini 128K Instruct | 96.730 of 30 items scored | 62.958.0–67.7 | 137–176 | 63.9ROCm 7.1 | 2.9 | 3–4B |
| 2 | SmolLM3-3B | 96.730 of 30 items scored | 78.073.0–83.1 | 71–142 | 22.2ROCm 7.1 | — | 3–4B |
4–9B
EXAONE-3.5-7.8B-Instruct leads its size class with 100.0 on a scale of 0 to 100; its Overall is 82.0 (95% interval 77.6–86.4).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | EXAONE-3.5-7.8B-Instruct | 100.030 of 30 items scored | 82.077.6–86.4 | 59–122 | 9.5ROCm 7.1 | 5.7 | 4–9B |
| 1 | Gemma4 E4B IT | 100.030 of 30 items scored | 95.593.0–97.7 | 2–51 | 13.2ROCm 7.1 | 7.9 | 4–9B |
| 1 | Granite3.1 Dense 8B Instruct | 100.030 of 30 items scored | 72.967.8–77.6 | 88–151 | 34.8ROCm 7.1 | 6.0 | 4–9B |
| 1 | Granite4.2 8B | 100.030 of 30 items scored | 81.977.2–86.3 | 59–128 | 11.1ROCm 7.1 | 6.4 | 4–9B |
| 1 | Nemotron 3.5 Bolt E4B | 100.030 of 30 items scored | 90.386.3–93.9 | 8–82 | 9.8ROCm 7.1 | 8.6 | 4–9B |
9–16B
Deepcoder 14B Preview leads its size class with 100.0 on a scale of 0 to 100; its Overall is 74.5 (95% interval 69.5–79.0).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | Deepcoder 14B Previewfine-tune of DeepSeek-R1-Distill-Qwen 14Bcode model | 100.030 of 30 items scored | 74.569.5–79.0 | 84–146 | 6.7ROCm 7.1 | 10.8 | 9–16B |
| 1 | DeepSeek-R1-Distill-Qwen-14B | 100.030 of 30 items scored | 85.381.2–89.2 | 38–106 | 7.1ROCm 7.1 | 10.8 | 9–16B |
| 1 | Gemma 4 12B IT | 100.030 of 30 items scored | 98.697.0–99.8 | 1–12 | 8.1ROCm 7.1 | 8.9 | 9–16B |
| 1 | Ornith-1.5-9B | 100.030 of 30 items scored | 89.085.4–92.4 | 19–81 | 8.1ROCm 7.1 | — | 9–16B |
| 1 | Qwen2.5-14B-Instruct | 100.030 of 30 items scored | 91.388.0–94.2 | 11–72 | 21.7ROCm 7.1 | 10.8 | 9–16B |
16–35B
Aya Expanse 32B leads its size class with 100.0 on a scale of 0 to 100; its Overall is 78.8 (95% interval 74.6–82.9).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | Aya Expanse 32B | 100.030 of 30 items scored | 78.874.6–82.9 | 72–137 | 10.0ROCm 7.1 | 23.8 | 16–35B |
| 1 | DeepSeek-R1-Distill-Qwen-32B | 100.030 of 30 items scored | 89.186.0–91.9 | 19–85 | 3.1ROCm 7.1 | 23.8 | 16–35B |
| 1 | Devstral 24B Small 2505code model | 100.030 of 30 items scored | 88.985.6–92.0 | 23–86 | 4.2ROCm 7.1 | 17.2 | 16–35B |
| 1 | Devstral Small 2 24B Instruct (2512)code model | 100.030 of 30 items scored | 92.189.3–94.7 | 9–67 | 3.1ROCm 7.1 | 18.2 | 16–35B |
| 1 | gemma-4-26B-A4B-it | 100.030 of 30 items scored | 97.895.8–99.3 | 1–22 | 15.7ROCm 7.1 | 21.6 | 16–35B |
> 35B
GLM-4.5-Air leads its size class with 100.0 on a scale of 0 to 100; its Overall is 92.8 (95% interval 89.7–95.6).
| Place | Model | Knowledge & honesty (0 to 100) | Overall | Rank range | Decode (tok/s) | Memory needed (GB, est.) | Size class |
|---|---|---|---|---|---|---|---|
| 1 | GLM-4.5-Air | 100.030 of 30 items scored | 92.889.7–95.6 | 6–68 | 6.0Vulkan | 87.6 | > 35B |
| 1 | gpt-oss-120b | 100.030 of 30 items scored | 98.696.8–100.0 | 1–14 | 11.0Vulkan | 78.4 | > 35B |
| 1 | Llama 4 Scout 17B-16E Instruct | 100.030 of 30 items scored | 93.690.7–96.1 | 4–65 | 17.0Vulkan | 80.9 | > 35B |
| 1 | Llama-3.3-70B-Instruct | 100.030 of 30 items scored | 94.391.3–96.7 | 4–63 | 1.4Vulkan | 51.0 | > 35B |
| 1 | Qwen3-Coder-Nextcode model | 100.030 of 30 items scored | 96.494.2–98.3 | 2–42 | 18.1Vulkan | 62.1 | > 35B |
A higher place is not always a clear win. When two models have overlapping rank ranges, this battery cannot tell them apart; see how sure a score is. A dash means not measured or not scored, which is different from 0. Speeds were measured on one laptop and are comparable only between models on the same backend.
More: all the best-model pages, the hardware picker, speed and memory for every model.