Skip to content

Benchmark Results - Overview

Here we collect the results of the living BioChatter benchmark. For an explanation, see the benchmarking documentation and the developer docs for further reading.

Scores per model

Table sorted by median score in descending order. Click the column names to reorder.

Model name Size Median Accuracy SD
claude-3-opus-20240229 Unknown 0.77 0.28
gpt-3.5-turbo-0125 175 0.77 0.19
gpt-3.5-turbo-0613 175 0.76 0.21
claude-3-5-sonnet-20240620 Unknown 0.76 0.28
gpt-4-0613 Unknown 0.73 0.17
gpt-4o-2024-08-06 Unknown 0.73 0.24
llama-3.1-instruct 70 0.73 0.29
llama-3.1-instruct 8 0.72 0.28
gpt-4-0125-preview Unknown 0.69 0.26
gpt-4o-mini-2024-07-18 Unknown 0.69 0.22
gpt-4-1106-preview Unknown 0.69 0.06
gpt-4o-2024-05-13 Unknown 0.68 0.31
gpt-4-turbo-2024-04-09 Unknown 0.68 0.27
llama-3-instruct 8 0.65 0.36
openhermes-2.5 7 0.6 0.3
gpt-4o-2024-11-20 Unknown 0.55 0.14
chatglm3 6 0.44 0.26
llama-2-chat 70 0.42 0.34
mistral-instruct-v0.2 7 0.4 0.33
code-llama-instruct 7 0.4 0.35
code-llama-instruct 34 0.38 0.35
code-llama-instruct 13 0.38 0.33
llama-2-chat 13 0.38 0.33
mixtral-instruct-v0.1 46,7 0.34 0.28
llama-2-chat 7 0.31 0.3

Scatter Quantisation Name Boxplot Model

Scores per quantisation

Table sorted by median score in descending order. Click the column names to reorder.

Model name Size Version Quantisation Median Accuracy SD
claude-3-opus-20240229 Unknown nan nan 0.77 0.28
gpt-3.5-turbo-0125 175 nan nan 0.77 0.19
claude-3-5-sonnet-20240620 Unknown nan nan 0.76 0.28
gpt-3.5-turbo-0613 175 nan nan 0.76 0.21
llama-3.1-instruct 8 ggufv2 Q6_K 0.74 0.28
llama-3.1-instruct 70 ggufv2 IQ2_M 0.74 0.29
llama-3.1-instruct 8 ggufv2 Q5_K_M 0.74 0.28
gpt-4-0613 Unknown nan nan 0.73 0.17
llama-3.1-instruct 70 ggufv2 IQ4_XS 0.73 0.29
gpt-4o-2024-08-06 Unknown nan nan 0.73 0.24
llama-3.1-instruct 8 ggufv2 Q8_0 0.72 0.3
llama-3.1-instruct 8 ggufv2 Q3_K_L 0.71 0.28
llama-3.1-instruct 8 ggufv2 Q4_K_M 0.7 0.26
llama-3.1-instruct 8 ggufv2 IQ4_XS 0.69 0.28
gpt-4-1106-preview Unknown nan nan 0.69 0.06
gpt-4-0125-preview Unknown nan nan 0.69 0.26
gpt-4o-mini-2024-07-18 Unknown nan nan 0.69 0.22
gpt-4-turbo-2024-04-09 Unknown nan nan 0.68 0.27
gpt-4o-2024-05-13 Unknown nan nan 0.68 0.31
llama-3.1-instruct 70 ggufv2 Q3_K_S 0.67 0.28
llama-3-instruct 8 ggufv2 Q8_0 0.65 0.35
llama-3-instruct 8 ggufv2 Q4_K_M 0.65 0.38
llama-3-instruct 8 ggufv2 Q6_K 0.65 0.36
openhermes-2.5 7 ggufv2 Q6_K 0.62 0.3
llama-3-instruct 8 ggufv2 Q5_K_M 0.62 0.36
openhermes-2.5 7 ggufv2 Q5_K_M 0.6 0.29
openhermes-2.5 7 ggufv2 Q8_0 0.6 0.3
openhermes-2.5 7 ggufv2 Q4_K_M 0.6 0.3
openhermes-2.5 7 ggufv2 Q3_K_M 0.56 0.3
gpt-4o-2024-11-20 Unknown nan nan 0.55 0.14
code-llama-instruct 34 ggufv2 Q2_K 0.5 0.33
openhermes-2.5 7 ggufv2 Q2_K 0.5 0.28
code-llama-instruct 7 ggufv2 Q3_K_M 0.49 0.31
code-llama-instruct 7 ggufv2 Q4_K_M 0.47 0.39
mistral-instruct-v0.2 7 ggufv2 Q5_K_M 0.46 0.34
mistral-instruct-v0.2 7 ggufv2 Q6_K 0.45 0.34
code-llama-instruct 34 ggufv2 Q3_K_M 0.45 0.31
chatglm3 6 ggmlv3 q4_0 0.44 0.26
llama-2-chat 70 ggufv2 Q5_K_M 0.44 0.35
llama-2-chat 70 ggufv2 Q4_K_M 0.44 0.35
code-llama-instruct 13 ggufv2 Q6_K 0.44 0.35
code-llama-instruct 13 ggufv2 Q8_0 0.44 0.33
code-llama-instruct 13 ggufv2 Q5_K_M 0.43 0.32
llama-2-chat 70 ggufv2 Q3_K_M 0.41 0.33
mistral-instruct-v0.2 7 ggufv2 Q3_K_M 0.41 0.34
mistral-instruct-v0.2 7 ggufv2 Q8_0 0.4 0.33
llama-2-chat 13 ggufv2 Q8_0 0.4 0.34
code-llama-instruct 7 ggufv2 Q8_0 0.4 0.37
code-llama-instruct 7 ggufv2 Q5_K_M 0.39 0.34
llama-2-chat 13 ggufv2 Q3_K_M 0.39 0.33
llama-2-chat 13 ggufv2 Q5_K_M 0.39 0.33
code-llama-instruct 7 ggufv2 Q2_K 0.38 0.29
code-llama-instruct 34 ggufv2 Q4_K_M 0.38 0.35
code-llama-instruct 7 ggufv2 Q6_K 0.38 0.39
code-llama-instruct 34 ggufv2 Q5_K_M 0.38 0.38
llama-2-chat 70 ggufv2 Q2_K 0.38 0.35
llama-2-chat 13 ggufv2 Q6_K 0.37 0.34
code-llama-instruct 34 ggufv2 Q8_0 0.37 0.35
mistral-instruct-v0.2 7 ggufv2 Q2_K 0.37 0.29
mistral-instruct-v0.2 7 ggufv2 Q4_K_M 0.37 0.35
code-llama-instruct 34 ggufv2 Q6_K 0.37 0.36
llama-2-chat 13 ggufv2 Q4_K_M 0.36 0.34
mixtral-instruct-v0.1 46,7 ggufv2 Q4_K_M 0.35 0.3
mixtral-instruct-v0.1 46,7 ggufv2 Q5_K_M 0.34 0.31
mixtral-instruct-v0.1 46,7 ggufv2 Q6_K 0.34 0.29
llama-2-chat 7 ggufv2 Q5_K_M 0.34 0.29
mixtral-instruct-v0.1 46,7 ggufv2 Q3_K_M 0.33 0.28
llama-2-chat 7 ggufv2 Q2_K 0.33 0.32
code-llama-instruct 13 ggufv2 Q4_K_M 0.33 0.31
mixtral-instruct-v0.1 46,7 ggufv2 Q8_0 0.33 0.25
mixtral-instruct-v0.1 46,7 ggufv2 Q2_K 0.32 0.27
llama-2-chat 7 ggufv2 Q8_0 0.31 0.28
llama-2-chat 7 ggufv2 Q6_K 0.31 0.29
llama-2-chat 7 ggufv2 Q4_K_M 0.3 0.29
llama-2-chat 7 ggufv2 Q3_K_M 0.3 0.33
llama-2-chat 13 ggufv2 Q2_K 0.28 0.29
code-llama-instruct 13 ggufv2 Q2_K 0.17 0.34
code-llama-instruct 13 ggufv2 Q3_K_M 0.15 0.34

Boxplot Quantisation

Scores of all tasks

Wide table; you may need to scroll horizontally to see all columns. Table sorted by median score in descending order. Click the column names to reorder.

Full model name property_selection naive_query_generation_using_schema query_generation python_api_calling entity_selection sourcedata_info_extraction python_api_calling_reduced medical_exam multimodal_answer property_exists explicit_relevance_of_single_fragments implicit_relevance_of_multiple_fragments end_to_end_query_generation relationship_selection api_calling Mean Accuracy Median Accuracy SD
claude-3-opus-20240229 0.421875 0.733333 0.944444 nan 1 0.691235 nan 0.805556 nan 1 0.833333 1 0.655556 0 nan 0.73503 0.770293 0.276411
gpt-3.5-turbo-0125 0.36747 0.514451 0.953757 0.615789 0.978261 0.510032 0.759615 0.671322 nan 0.789474 1 0.9 0.919075 1 0.746479 0.766123 0.766123 0.191717
claude-3-5-sonnet-20240620 0.375 0.633333 0.966667 nan 1 0.756088 nan 0.7737 nan 0.866667 1 1 0.733333 0 nan 0.736799 0.764894 0.283502
gpt-3.5-turbo-0613 0.3625 0.5 0.946667 nan 0.888889 0.575381 nan nan nan 0.755556 1 1 0.833333 0.5 nan 0.736233 0.755556 0.211926
llama-3.1-instruct:8:ggufv2:Q6_K 0.46875 0.633333 0.955556 nan 1 0.394469 nan 0.751748 nan 0.833333 1 0.833333 0.733333 0 nan 0.69126 0.742541 0.278015
llama-3.1-instruct:70:ggufv2:IQ2_M 0.328125 0.633333 0.955556 nan 1 0.626498 nan 0.772881 nan 0.916667 1 1 0.6 0 nan 0.712096 0.742489 0.293676
llama-3.1-instruct:8:ggufv2:Q5_K_M 0.4375 0.7 0.933333 nan 1 0.380477 nan 0.749117 nan 0.833333 1 0.833333 0.733333 0 nan 0.690948 0.741225 0.279278
gpt-4-0613 0.38253 0.682081 0.959538 0.489474 0.920635 0.668903 0.769231 0.730912 nan 0.666667 1 1 0.878613 0.695652 0.619048 0.747377 0.730912 0.174471
llama-3.1-instruct:70:ggufv2:IQ4_XS 0.375 0.566667 0.955556 nan 1 0.699238 nan 0.822581 nan 0.75 1 1 0.6 0 nan 0.706276 0.728138 0.285226
gpt-4o-2024-08-06 0.425439 0.528302 0.874214 0.363158 1 0.711185 0.740385 0.850211 nan 0.179894 1 0.666667 0.830189 1 nan 0.705357 0.725785 0.243719
llama-3.1-instruct:8:ggufv2:Q8_0 0.565789 0.660377 0.937107 nan 1 0.38907 nan 0.765734 nan 0.161765 1 1 0.773585 0.142857 nan 0.67239 0.719062 0.295232
llama-3.1-instruct:8:ggufv2:Q3_K_L 0.486842 0.622642 0.943396 nan 1 0.360379 nan 0.768421 nan 0.24 1 0.833333 0.811321 0.142857 nan 0.655381 0.711901 0.280463
llama-3.1-instruct:8:ggufv2:Q4_K_M 0.513158 0.660377 0.924528 nan 0.92 0.382027 nan 0.741935 nan 0.150538 1 0.833333 0.735849 0.285714 nan 0.649769 0.698113 0.257418
llama-3.1-instruct:8:ggufv2:IQ4_XS 0.387255 0.646018 0.946903 nan 0.893939 0.414621 nan 0.756944 nan 0.439394 1 0.833333 0.743363 0 nan 0.641979 0.69469 0.276449
gpt-4-1106-preview nan nan nan 0.616216 nan nan 0.767677 nan nan nan nan nan nan nan nan 0.691946 0.691946 0.0618335
gpt-4-0125-preview 0.0301205 0.456647 0.83815 0.508772 0.824561 0.689705 0.769231 0.777159 nan 0.619048 1 0.5 0.109827 0.782609 0.793651 0.621391 0.689705 0.259268
gpt-4o-mini-2024-07-18 0.388554 0.537572 0.953757 0.578947 0.921053 0.684553 0.730769 0.840796 0.98 0.52439 0.833333 0.5 0.687861 0.130435 0.714286 0.667087 0.686207 0.216242
gpt-4-turbo-2024-04-09 0.325301 0.508671 0.83237 0.259649 1 0.650369 0.762821 0.83701 0.99 0.657143 1 1 0.635838 0.130435 nan 0.684972 0.684972 0.270175
gpt-4o-2024-05-13 0.0301205 0.537572 0.809249 nan 1 0.653946 nan 0.763501 0.96 0.526316 1 0.7 0.115607 0.130435 0.809524 0.618175 0.676973 0.312259
llama-3.1-instruct:70:ggufv2:Q3_K_S 0.375 0.633333 0.966667 nan 1 0.642336 nan 0.8 nan 0.625 1 1 0.6 0 nan 0.694758 0.668547 0.28438
llama-3-instruct:8:ggufv2:Q8_0 0.28125 0.666667 0.92 nan 0.875 0.188555 nan 0.640669 nan 0.725 1 1 0 0 nan 0.572467 0.653668 0.35454
llama-3-instruct:8:ggufv2:Q4_K_M 0.109375 0.666667 0.92 nan 0.861111 0.116871 nan 0.624884 nan 0.775 1 1 0 0 nan 0.552173 0.645775 0.376754
llama-3-instruct:8:ggufv2:Q6_K 0.28125 0.666667 0.926667 nan 0.875 0.162657 nan 0.623955 nan 0.775 1 1 0 0 nan 0.573745 0.645311 0.359165
openhermes-2.5:7:ggufv2:Q6_K 0.126404 0.557078 0.890411 nan 0.7675 0.619167 nan 0.57423 nan 0.113379 1 1 0.273973 0.896552 nan 0.619881 0.619524 0.300867
llama-3-instruct:8:ggufv2:Q5_K_M 0.1875 0.6 0.926667 nan 0.875 0.166434 nan 0.635097 nan 0.65 1 1 0 0 nan 0.549154 0.617549 0.360565
openhermes-2.5:7:ggufv2:Q5_K_M 0.196629 0.56621 0.917808 nan 0.758808 0.579916 nan 0.571429 nan 0.120988 1 1 0.26484 0.896552 nan 0.624835 0.602375 0.293641
openhermes-2.5:7:ggufv2:Q8_0 0.196629 0.497717 0.90411 nan 0.628118 0.600829 nan 0.577031 nan 0.100629 1 1 0.237443 0.896552 nan 0.603551 0.60219 0.296591
openhermes-2.5:7:ggufv2:Q4_K_M 0.126404 0.479452 0.894977 nan 0.66967 0.597281 nan 0.586368 nan 0.140921 1 1 0.246575 0.896552 nan 0.603473 0.600377 0.299216
openhermes-2.5:7:ggufv2:Q3_K_M 0.171348 0.47032 0.917808 nan 1 0.554488 nan 0.563959 nan 0.156805 1 0.5 0.287671 1 nan 0.602036 0.559223 0.301462
gpt-4o-2024-11-20 nan nan nan 0.377193 nan nan 0.730769 nan nan nan nan nan nan nan nan 0.553981 0.553981 0.144347
code-llama-instruct:34:ggufv2:Q2_K 0 0.566667 0.686667 nan 0 nan nan nan nan 0.75 0.5 1 0 0.5 nan 0.444815 0.5 0.328199
openhermes-2.5:7:ggufv2:Q2_K 0.0168539 0.420091 0.917808 nan 0.604444 0.444054 nan 0.539106 nan 0.18638 1 0.5 0.159817 0.655172 nan 0.494884 0.497442 0.27656
code-llama-instruct:7:ggufv2:Q3_K_M 0 0.426667 0.873333 nan 0.5 nan nan nan nan 0.8 0.833333 0.7 0 0.25 nan 0.487037 0.493519 0.307716
code-llama-instruct:7:ggufv2:Q4_K_M 0 0.653333 0.966667 nan 0.333333 0.138732 nan nan nan 0.6 1 1 0 0 nan 0.469207 0.469207 0.38731
mistral-instruct-v0.2:7:ggufv2:Q5_K_M 0 0.466667 0.826667 nan 0.444444 0.385754 nan 0.364146 nan 0.688889 1 1 0 0 nan 0.470597 0.455556 0.34385
mistral-instruct-v0.2:7:ggufv2:Q6_K 0.046875 0.433333 0.833333 nan 0.5 0.367412 nan 0.366947 nan 0.65 1 1 0 0 nan 0.472536 0.452935 0.337974
code-llama-instruct:34:ggufv2:Q3_K_M 0 0.6 0.786667 nan 0 nan nan nan nan 0.875 0.5 0.5 0 0.25 nan 0.390185 0.445093 0.306514
chatglm3:6:ggmlv3:q4_0 0.2875 0.48 0.553333 nan 0.75 0.188284 nan 0.426704 nan 0.275 0.733333 1 0 0.4 nan 0.463105 0.444905 0.260423
llama-2-chat:70:ggufv2:Q5_K_M 0 0.36 0.906667 nan 0.444444 0.210166 nan nan nan 0.777778 1 0.9 0 0.25 nan 0.484905 0.444444 0.346535
llama-2-chat:70:ggufv2:Q4_K_M 0 0.42 0.92 nan 0.444444 0.240936 nan nan nan 0.755556 1 1 0 0.25 nan 0.503094 0.444444 0.354692
code-llama-instruct:13:ggufv2:Q6_K 0 0.54 0.793333 nan 0 nan nan nan nan 0.825 0.833333 0.5 0 0 nan 0.387963 0.443981 0.345581
code-llama-instruct:13:ggufv2:Q8_0 0 0.566667 0.766667 nan 0 nan nan nan nan 0.75 0.833333 0.5 0 0 nan 0.37963 0.439815 0.334971
code-llama-instruct:13:ggufv2:Q5_K_M 0 0.566667 0.78 nan 0 nan nan nan nan 0.775 0.666667 0.5 0 0 nan 0.36537 0.432685 0.320506
llama-2-chat:70:ggufv2:Q3_K_M 0.171875 0.413333 0.906667 nan 0.333333 0.197898 nan nan nan 0.777778 1 0.5 0 0 nan 0.430088 0.413333 0.327267
mistral-instruct-v0.2:7:ggufv2:Q3_K_M 0.046875 0.466667 0.773333 nan 0.333333 0.368974 nan 0.360411 nan 0.666667 1 1 0 0 nan 0.456024 0.412499 0.335885
mistral-instruct-v0.2:7:ggufv2:Q8_0 0.0375 0.433333 0.846667 nan 0.333333 0.351684 nan 0.366947 nan 0.644444 1 0.9 0 0 nan 0.446719 0.40014 0.330107
llama-2-chat:13:ggufv2:Q8_0 0 0.48 0.786667 nan 0 0.0762457 nan 0.431373 nan 0.711111 1 0.5 0 0 nan 0.362309 0.396841 0.335904
code-llama-instruct:7:ggufv2:Q8_0 0 0.4 0.96 nan 0 nan nan nan nan 0.666667 1 0.5 0 0 nan 0.391852 0.395926 0.37338
code-llama-instruct:7:ggufv2:Q5_K_M 0 0.4 0.96 nan 0.111111 nan nan nan nan 0.688889 0.833333 0.5 0 0 nan 0.388148 0.394074 0.340156
llama-2-chat:13:ggufv2:Q3_K_M 0 0.48 0.68 nan 0 0.112631 nan 0.428571 nan 0.733333 1 0.5 0 0 nan 0.357685 0.393128 0.325419
llama-2-chat:13:ggufv2:Q5_K_M 0 0.433333 0.746667 nan 0 0.0766167 nan 0.431373 nan 0.644444 1 0.5 0 0 nan 0.348403 0.389888 0.32518
code-llama-instruct:7:ggufv2:Q2_K 0.0625 0.533333 0.92 nan 0.25 nan nan nan nan 0.8 0.333333 0.7 0 0.25 nan 0.427685 0.380509 0.292686
code-llama-instruct:34:ggufv2:Q4_K_M 0 0.466667 0.906667 nan 0 nan nan nan nan 0.975 0.5 0.4 0 0 nan 0.360926 0.380463 0.350483
code-llama-instruct:7:ggufv2:Q6_K 0 0.333333 0.96 nan 0 nan nan nan nan 0.775 0.833333 0.9 0 0 nan 0.422407 0.37787 0.391629
code-llama-instruct:34:ggufv2:Q5_K_M 0 0.466667 0.9 nan 0.125 nan nan nan nan 0.95 0.333333 1 0 0 nan 0.419444 0.376389 0.384096
llama-2-chat:70:ggufv2:Q2_K 0 0.473333 0.9 nan 0 0.215047 nan nan nan 0.666667 1 0.5 0 0 nan 0.375505 0.375505 0.352226
llama-2-chat:13:ggufv2:Q6_K 0 0.386667 0.813333 nan 0 0.0781337 nan 0.428571 nan 0.775 1 0.5 0 0 nan 0.361973 0.37432 0.342819
code-llama-instruct:34:ggufv2:Q8_0 0 0.466667 0.86 nan 0.25 nan nan nan nan 0.925 0.333333 0.9 0 0 nan 0.415 0.374167 0.353285
mistral-instruct-v0.2:7:ggufv2:Q2_K 0 0.573333 0.693333 nan 0.222222 0.331261 nan 0.352941 nan 0.6 1 0.5 0 0 nan 0.388463 0.370702 0.294881
mistral-instruct-v0.2:7:ggufv2:Q4_K_M 0 0.366667 0.826667 nan 0.333333 0.347025 nan 0.365079 nan 0.688889 1 1 0 0 nan 0.447969 0.365873 0.348328
code-llama-instruct:34:ggufv2:Q6_K 0 0.473333 0.853333 nan 0.125 nan nan nan nan 0.9 0.333333 0.9 0 0 nan 0.398333 0.365833 0.356636
llama-2-chat:13:ggufv2:Q4_K_M 0 0.366667 0.76 nan 0 0.0888675 nan 0.428571 nan 0.777778 1 0.5 0 0 nan 0.356535 0.361601 0.336686
mixtral-instruct-v0.1:46_7:ggufv2:Q4_K_M 0.1625 0.426667 0.76 nan 0.333333 0.193786 nan 0.368814 nan 0.755556 0.166667 1 0 0 nan 0.378848 0.351074 0.301567
mixtral-instruct-v0.1:46_7:ggufv2:Q5_K_M 0 0.333333 0.84 nan 0.422222 0.235659 nan 0.352941 nan 0.711111 0 1 0 0.25 nan 0.376842 0.343137 0.313874
mixtral-instruct-v0.1:46_7:ggufv2:Q6_K 0 0.333333 0.826667 nan 0.475 0.225524 nan 0.34267 nan 0.85 0 0.7 0 0.25 nan 0.363927 0.338002 0.289705
llama-2-chat:7:ggufv2:Q5_K_M 0.0337079 0.3379 0.547945 nan 0.57037 0.0697591 nan 0.40056 nan 0.155556 1 0.6 0 0 nan 0.3378 0.33785 0.293711
mixtral-instruct-v0.1:46_7:ggufv2:Q3_K_M 0.065625 0.38 0.893333 nan 0.333333 0.229622 nan nan nan 0.777778 0 0.5 0 0.25 nan 0.342969 0.333333 0.278279
llama-2-chat:7:ggufv2:Q2_K 0 0.164384 0.611872 nan 0.410256 0.0361865 nan 0.369748 nan 0.324786 0.833333 1 0 0 nan 0.340961 0.332873 0.320018
code-llama-instruct:13:ggufv2:Q4_K_M 0 0.533333 0.833333 nan 0 nan nan nan nan 0.775 0.333333 0.5 0 0 nan 0.330556 0.331944 0.30939
mixtral-instruct-v0.1:46_7:ggufv2:Q8_0 0 0.386667 0.846667 nan 0.311111 0.189177 nan 0.358543 nan 0.666667 0.133333 0.6 0 0.25 nan 0.340197 0.325654 0.248216
mixtral-instruct-v0.1:46_7:ggufv2:Q2_K 0 0.48 0.726667 nan 0 0.157514 nan 0.329599 nan 0.733333 0.333333 0.6 0 0 nan 0.305495 0.317547 0.269925
llama-2-chat:7:ggufv2:Q8_0 0 0.292237 0.589041 nan 0.481481 0.0847297 nan 0.40056 nan 0.163399 1 0.5 0 0.103448 nan 0.328627 0.310432 0.278624
llama-2-chat:7:ggufv2:Q6_K 0 0.292237 0.561644 nan 0.553846 0.0614608 nan 0.406162 nan 0.177778 1 0.5 0 0 nan 0.323012 0.307625 0.290181
llama-2-chat:7:ggufv2:Q4_K_M 0 0.273973 0.611872 nan 0.57037 0.0852494 nan 0.40056 nan 0.251852 1 0.5 0 0 nan 0.335807 0.30489 0.291028
llama-2-chat:7:ggufv2:Q3_K_M 0.0898876 0.228311 0.589041 nan 0.435897 0.0650717 nan 0.394958 nan 0.207407 1 1 0 0.103448 nan 0.374002 0.301156 0.326263
llama-2-chat:13:ggufv2:Q2_K 0 0.366667 0.433333 nan 0 0.0649389 nan 0.414566 nan 0.288889 1 0.5 0 0 nan 0.278945 0.283917 0.285171
code-llama-instruct:13:ggufv2:Q2_K 0 0.566667 0.82 nan 0 nan nan nan nan 0.875 0.0333333 0.4 0 0 nan 0.299444 0.166389 0.336056
code-llama-instruct:13:ggufv2:Q3_K_M 0 0.533333 0.833333 nan 0.45 nan nan nan nan 0.85 0 0 0 0 nan 0.296296 0.148148 0.336707