Commit
·
90ec376
1
Parent(s):
3999c2c
- src/lib/benchmarks/ index.ts +2 -1
- src/lib/benchmarks/qwen.ts +720 -0
src/lib/benchmarks/ index.ts
CHANGED
|
@@ -4,6 +4,7 @@ import { googleBenchmarks } from "./google";
|
|
| 4 |
import { anthropicBenchmarks } from "./anthropic";
|
| 5 |
import { openaiBenchmarks } from "./openai";
|
| 6 |
import { deepseekBenchmarks } from "./deepseek";
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
export const benchmarkData: Benchmark[] = [
|
|
@@ -12,5 +13,5 @@ export const benchmarkData: Benchmark[] = [
|
|
| 12 |
...anthropicBenchmarks,
|
| 13 |
...openaiBenchmarks,
|
| 14 |
...deepseekBenchmarks,
|
| 15 |
-
|
| 16 |
];
|
|
|
|
| 4 |
import { anthropicBenchmarks } from "./anthropic";
|
| 5 |
import { openaiBenchmarks } from "./openai";
|
| 6 |
import { deepseekBenchmarks } from "./deepseek";
|
| 7 |
+
import { qwenBenchmarks } from "./qwen";
|
| 8 |
|
| 9 |
|
| 10 |
export const benchmarkData: Benchmark[] = [
|
|
|
|
| 13 |
...anthropicBenchmarks,
|
| 14 |
...openaiBenchmarks,
|
| 15 |
...deepseekBenchmarks,
|
| 16 |
+
...qwenBenchmarks,
|
| 17 |
];
|
src/lib/benchmarks/qwen.ts
ADDED
|
@@ -0,0 +1,720 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
import { Benchmark } from "./types";
|
| 3 |
+
|
| 4 |
+
export const qwenBenchmarks: Benchmark[] = [
|
| 5 |
+
{
|
| 6 |
+
model: "Qwen3-235B-A22B (Base Model)",
|
| 7 |
+
provider: "Qwen",
|
| 8 |
+
inputPrice: 0,
|
| 9 |
+
outputPrice: 0,
|
| 10 |
+
benchmark: {
|
| 11 |
+
mmlu: 87.81,
|
| 12 |
+
//mmluredux: 87.40,
|
| 13 |
+
////"mmlu-pro": 68.18,
|
| 14 |
+
////supergpqa: 44.06,
|
| 15 |
+
////bbh: 88.87,
|
| 16 |
+
gpqa: 47.47,
|
| 17 |
+
////gsm8k: 94.39,
|
| 18 |
+
////math: 71.84,
|
| 19 |
+
////evalplus: 77.60,
|
| 20 |
+
//multiple: 65.94,
|
| 21 |
+
mbpp: 81.40,
|
| 22 |
+
//cruxo: 79.00,
|
| 23 |
+
////mgsm: 83.53,
|
| 24 |
+
mmmlu: 86.70,
|
| 25 |
+
////include: 73.46,
|
| 26 |
+
},
|
| 27 |
+
source: "",
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
model: "Qwen3-32B (Base Model)",
|
| 31 |
+
provider: "Qwen",
|
| 32 |
+
inputPrice: 0,
|
| 33 |
+
outputPrice: 0,
|
| 34 |
+
benchmark: {
|
| 35 |
+
mmlu: 83.61,
|
| 36 |
+
//"mmlu-redux": 83.41,
|
| 37 |
+
//"mmlu-pro": 65.54,
|
| 38 |
+
//supergpqa: 39.78,
|
| 39 |
+
//bbh: 87.38,
|
| 40 |
+
gpqa: 49.49,
|
| 41 |
+
//gsm8k: 93.40,
|
| 42 |
+
//math: 61.62,
|
| 43 |
+
//evalplus: 72.05,
|
| 44 |
+
//"multipl-e":: 67.06,
|
| 45 |
+
mbpp: 78.20,
|
| 46 |
+
// "crux-o":: 72.50,
|
| 47 |
+
//mgsm: 83.06,
|
| 48 |
+
mmmlu: 83.83,
|
| 49 |
+
//include: 67.87,
|
| 50 |
+
},
|
| 51 |
+
source: "",
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
model: "Qwen3-14B (Base Model)",
|
| 55 |
+
provider: "Qwen",
|
| 56 |
+
inputPrice: 0,
|
| 57 |
+
outputPrice: 0,
|
| 58 |
+
benchmark: {
|
| 59 |
+
mmlu: 81.05,
|
| 60 |
+
//"mmlu-redux": 79.88,
|
| 61 |
+
//"mmlu-pro": 61.03,
|
| 62 |
+
//supergpqa: 34.27,
|
| 63 |
+
//bbh: 81.07,
|
| 64 |
+
gpqa: 39.90,
|
| 65 |
+
//gsm8k: 92.49,
|
| 66 |
+
//math: 62.02,
|
| 67 |
+
//evalplus: 72.23,
|
| 68 |
+
//"multipl-e":: 61.69,
|
| 69 |
+
mbpp: 73.40,
|
| 70 |
+
// "crux-o":: 68.60,
|
| 71 |
+
//mgsm: 79.20,
|
| 72 |
+
mmmlu: 81.46,
|
| 73 |
+
//include: 64.55,
|
| 74 |
+
},
|
| 75 |
+
source: "",
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
model: "Qwen3-30B-A3B (Base Model)",
|
| 79 |
+
provider: "Qwen",
|
| 80 |
+
inputPrice: 0,
|
| 81 |
+
outputPrice: 0,
|
| 82 |
+
benchmark: {
|
| 83 |
+
mmlu: 81.38,
|
| 84 |
+
//"mmlu-redux": 81.17,
|
| 85 |
+
//"mmlu-pro": 61.49,
|
| 86 |
+
//supergpqa: 35.72,
|
| 87 |
+
//bbh: 81.54,
|
| 88 |
+
gpqa: 43.94,
|
| 89 |
+
//gsm8k: 91.81,
|
| 90 |
+
//math: 59.04,
|
| 91 |
+
//evalplus: 71.45,
|
| 92 |
+
//"multipl-e":: 66.53,
|
| 93 |
+
mbpp: 74.40,
|
| 94 |
+
// "crux-o":: 67.20,
|
| 95 |
+
//mgsm: 79.11,
|
| 96 |
+
mmmlu: 81.46,
|
| 97 |
+
//include: 67.00,
|
| 98 |
+
},
|
| 99 |
+
source: "",
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
model: "Qwen3-8B (Base Model)",
|
| 103 |
+
provider: "Qwen",
|
| 104 |
+
inputPrice: 0,
|
| 105 |
+
outputPrice: 0,
|
| 106 |
+
benchmark: {
|
| 107 |
+
mmlu: 76.89,
|
| 108 |
+
//"mmlu-redux": 76.17,
|
| 109 |
+
//"mmlu-pro": 56.73,
|
| 110 |
+
//supergpqa: 31.64,
|
| 111 |
+
//bbh: 78.40,
|
| 112 |
+
gpqa: 44.44,
|
| 113 |
+
//gsm8k: 89.84,
|
| 114 |
+
//math: 60.80,
|
| 115 |
+
//evalplus: 67.65,
|
| 116 |
+
//"multipl-e":: 58.75,
|
| 117 |
+
mbpp: 69.80,
|
| 118 |
+
// "crux-o":: 62.00,
|
| 119 |
+
//mgsm: 76.02,
|
| 120 |
+
mmmlu: 75.72,
|
| 121 |
+
//include: 59.40,
|
| 122 |
+
},
|
| 123 |
+
source: "",
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
model: "Qwen3-4B (Base Model)",
|
| 127 |
+
provider: "Qwen",
|
| 128 |
+
inputPrice: 0,
|
| 129 |
+
outputPrice: 0,
|
| 130 |
+
benchmark: {
|
| 131 |
+
mmlu: 72.99,
|
| 132 |
+
//"mmlu-redux": 72.79,
|
| 133 |
+
//"mmlu-pro": 50.58,
|
| 134 |
+
//supergpqa: 28.43,
|
| 135 |
+
//bbh: 72.59,
|
| 136 |
+
gpqa: 36.87,
|
| 137 |
+
//gsm8k: 87.79,
|
| 138 |
+
//math: 54.10,
|
| 139 |
+
//evalplus: 63.53,
|
| 140 |
+
//"multipl-e":: 53.13,
|
| 141 |
+
mbpp: 67.00,
|
| 142 |
+
// "crux-o":: 55.00,
|
| 143 |
+
//mgsm: 67.74,
|
| 144 |
+
mmmlu: 71.42,
|
| 145 |
+
//include: 56.29,
|
| 146 |
+
},
|
| 147 |
+
source: "",
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
model: "Qwen3-1.7B (Base Model)",
|
| 151 |
+
provider: "Qwen",
|
| 152 |
+
inputPrice: 0,
|
| 153 |
+
outputPrice: 0,
|
| 154 |
+
benchmark: {
|
| 155 |
+
mmlu: 62.63,
|
| 156 |
+
//"mmlu-redux": 61.66,
|
| 157 |
+
//"mmlu-pro": 36.76,
|
| 158 |
+
//supergpqa: 20.92,
|
| 159 |
+
//bbh: 54.47,
|
| 160 |
+
gpqa: 28.28,
|
| 161 |
+
//gsm8k: 75.44,
|
| 162 |
+
//math: 43.50,
|
| 163 |
+
//evalplus: 52.70,
|
| 164 |
+
//"multipl-e":: 42.71,
|
| 165 |
+
mbpp: 55.40,
|
| 166 |
+
// "crux-o":: 36.40,
|
| 167 |
+
//mgsm: 50.71,
|
| 168 |
+
mmmlu: 63.27,
|
| 169 |
+
//include: 45.57,
|
| 170 |
+
},
|
| 171 |
+
source: "",
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
model: "Qwen3-0.6B (Base Model)",
|
| 175 |
+
provider: "Qwen",
|
| 176 |
+
inputPrice: 0,
|
| 177 |
+
outputPrice: 0,
|
| 178 |
+
benchmark: {
|
| 179 |
+
mmlu: 52.81,
|
| 180 |
+
//"mmlu-redux": 51.26,
|
| 181 |
+
//"mmlu-pro": 24.74,
|
| 182 |
+
//supergpqa: 15.03,
|
| 183 |
+
//bbh: 41.47,
|
| 184 |
+
gpqa: 26.77,
|
| 185 |
+
//gsm8k: 59.59,
|
| 186 |
+
//math: 32.44,
|
| 187 |
+
//evalplus: 36.23,
|
| 188 |
+
//"multipl-e":: 24.58,
|
| 189 |
+
mbpp: 36.60,
|
| 190 |
+
// "crux-o":: 27.00,
|
| 191 |
+
//mgsm: 30.99,
|
| 192 |
+
mmmlu: 50.16,
|
| 193 |
+
//include: 34.26,
|
| 194 |
+
},
|
| 195 |
+
source: "",
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
model: "Qwen3-235B-A22B (Thinking Mode)",
|
| 199 |
+
provider: "Qwen",
|
| 200 |
+
inputPrice: 0,
|
| 201 |
+
outputPrice: 0,
|
| 202 |
+
benchmark: {
|
| 203 |
+
//"mmlu-redux": 92.7,
|
| 204 |
+
gpqa_diamond: 71.1,
|
| 205 |
+
//"c-eval": 89.6,
|
| 206 |
+
//"livebench-2024-11-25": 77.1,
|
| 207 |
+
//"ifeval-strict-prompt": 83.4,
|
| 208 |
+
|
| 209 |
+
//"arena-hard": 95.6,
|
| 210 |
+
//"alignbench-v1.1": 8.94,
|
| 211 |
+
//"creative-writing-v3": 84.6,
|
| 212 |
+
//writingbench: 8.03,
|
| 213 |
+
//"math-500": 98.0,
|
| 214 |
+
aime_24: 85.7,
|
| 215 |
+
aime_2025: 81.5,
|
| 216 |
+
//zebralogic: 80.3,
|
| 217 |
+
//autologi: 89.0,
|
| 218 |
+
//"bfcl-v3": 70.8,
|
| 219 |
+
//"livecodebench-v5": 70.7,
|
| 220 |
+
//"codeforces-rating": 2056,
|
| 221 |
+
//"codeforces-percentile": 98.2,
|
| 222 |
+
//"multi-if": 71.9,
|
| 223 |
+
//include: 78.7,
|
| 224 |
+
// "mmmlu-14-languages": 84.3,
|
| 225 |
+
//"mt-aime2024": 80.8,
|
| 226 |
+
//poly//math: 54.7,
|
| 227 |
+
//mlogiqa: 77.1,
|
| 228 |
+
},
|
| 229 |
+
source: "",
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
model: "Qwen3-235B-A22B (Non-thinking Mode)",
|
| 233 |
+
provider: "Qwen",
|
| 234 |
+
inputPrice: 0,
|
| 235 |
+
outputPrice: 0,
|
| 236 |
+
benchmark: {
|
| 237 |
+
//"mmlu-redux": 89.2,
|
| 238 |
+
gpqa_diamond: 62.9,
|
| 239 |
+
//"c-eval": 86.1,
|
| 240 |
+
//"livebench-2024-11-25": 62.5,
|
| 241 |
+
//"ifeval-strict-prompt": 83.2,
|
| 242 |
+
//"arena-hard": 96.1,
|
| 243 |
+
//"alignbench-v1.1": 8.91,
|
| 244 |
+
//"creative-writing-v3": 80.4,
|
| 245 |
+
//writingbench: 7.70,
|
| 246 |
+
//"math-500": 91.2,
|
| 247 |
+
|
| 248 |
+
aime_24: 40.1,
|
| 249 |
+
|
| 250 |
+
aime_2025: 24.7,
|
| 251 |
+
//zebralogic: 37.7,
|
| 252 |
+
//autologi: 83.3,
|
| 253 |
+
//"bfcl-v3": 68.0,
|
| 254 |
+
//"livecodebench-v5": 35.3,
|
| 255 |
+
//"codeforces-rating": 1387,
|
| 256 |
+
//"codeforces-percentile": 75.7,
|
| 257 |
+
//"multi-if": 70.2,
|
| 258 |
+
//include: 75.6,
|
| 259 |
+
// "mmmlu-14-languages": 79.8,
|
| 260 |
+
//"mt-aime2024": 32.4,
|
| 261 |
+
//poly//math: 27.0,
|
| 262 |
+
//mlogiqa: 67.6,
|
| 263 |
+
},
|
| 264 |
+
source: "",
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
model: "Qwen3-32B (Thinking Mode)",
|
| 268 |
+
provider: "Qwen",
|
| 269 |
+
inputPrice: 0,
|
| 270 |
+
outputPrice: 0,
|
| 271 |
+
benchmark: {
|
| 272 |
+
//"mmlu-redux": 90.9,
|
| 273 |
+
gpqa_diamond: 68.4,
|
| 274 |
+
//"c-eval": 87.3,
|
| 275 |
+
//"livebench-2024-11-25": 74.9,
|
| 276 |
+
//"ifeval-strict-prompt": 85.0,
|
| 277 |
+
//"arena-hard": 93.8,
|
| 278 |
+
//"alignbench-v1.1": 8.72,
|
| 279 |
+
//"creative-writing-v3": 81.0,
|
| 280 |
+
//writingbench: 7.90,
|
| 281 |
+
//"math-500": 97.2,
|
| 282 |
+
aime_24: 81.4,
|
| 283 |
+
aime_2025: 72.9,
|
| 284 |
+
//zebralogic: 88.8,
|
| 285 |
+
//autologi: 87.3,
|
| 286 |
+
//"bfcl-v3": 70.3,
|
| 287 |
+
//"livecodebench-v5": 65.7,
|
| 288 |
+
//"codeforces-rating": 1977,
|
| 289 |
+
//"codeforces-percentile": 97.7,
|
| 290 |
+
//"multi-if": 73.0,
|
| 291 |
+
//include: 73.7,
|
| 292 |
+
// "mmmlu-14-languages": 80.6,
|
| 293 |
+
//"mt-aime2024": 75.0,
|
| 294 |
+
//poly//math: 47.4,
|
| 295 |
+
//mlogiqa: 76.3,
|
| 296 |
+
},
|
| 297 |
+
source: "",
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
model: "Qwen3-32B (Non-thinking Mode)",
|
| 301 |
+
provider: "Qwen",
|
| 302 |
+
inputPrice: 0,
|
| 303 |
+
outputPrice: 0,
|
| 304 |
+
benchmark: {
|
| 305 |
+
//"mmlu-redux": 85.7,
|
| 306 |
+
gpqa_diamond: 54.6,
|
| 307 |
+
//"c-eval": 83.3,
|
| 308 |
+
//"livebench-2024-11-25": 59.8,
|
| 309 |
+
//"ifeval-strict-prompt": 83.2,
|
| 310 |
+
//"arena-hard": 92.8,
|
| 311 |
+
//"alignbench-v1.1": 8.58,
|
| 312 |
+
//"creative-writing-v3": 78.3,
|
| 313 |
+
//writingbench: 7.54,
|
| 314 |
+
//"math-500": 88.6,
|
| 315 |
+
aime_24: 31.0,
|
| 316 |
+
aime_2025: 20.2,
|
| 317 |
+
//zebralogic: 29.2,
|
| 318 |
+
//autologi: 78.5,
|
| 319 |
+
//"bfcl-v3": 63.0,
|
| 320 |
+
|
| 321 |
+
//"livecodebench-v5": 31.3,
|
| 322 |
+
//"codeforces-rating": 1353,
|
| 323 |
+
//"codeforces-percentile": 71.0,
|
| 324 |
+
//"multi-if": 70.7,
|
| 325 |
+
//include: 70.9,
|
| 326 |
+
// "mmmlu-14-languages": 76.5,
|
| 327 |
+
//"mt-aime2024": 24.1,
|
| 328 |
+
//poly//math: 22.5,
|
| 329 |
+
//mlogiqa: 62.9,
|
| 330 |
+
},
|
| 331 |
+
source: "",
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
model: "Qwen3-14B (Thinking Mode)",
|
| 335 |
+
provider: "Qwen",
|
| 336 |
+
inputPrice: 0,
|
| 337 |
+
outputPrice: 0,
|
| 338 |
+
benchmark: {
|
| 339 |
+
//"mmlu-redux": 88.6,
|
| 340 |
+
gpqa_diamond: 64.0,
|
| 341 |
+
//"c-eval": 86.2,
|
| 342 |
+
//"livebench-2024-11-25": 71.3,
|
| 343 |
+
//"ifeval-strict-prompt": 85.4,
|
| 344 |
+
//"arena-hard": 91.7,
|
| 345 |
+
//"alignbench-v1.1": 8.56,
|
| 346 |
+
//"creative-writing-v3": 80.3,
|
| 347 |
+
//writingbench: 7.80,
|
| 348 |
+
//"math-500": 96.8,
|
| 349 |
+
aime_24: 79.3,
|
| 350 |
+
aime_2025: 70.4,
|
| 351 |
+
//zebralogic: 88.5,
|
| 352 |
+
//autologi: 89.2,
|
| 353 |
+
//"bfcl-v3": 70.4,
|
| 354 |
+
//"livecodebench-v5": 63.5,
|
| 355 |
+
//"codeforces-rating": 1766,
|
| 356 |
+
//"codeforces-percentile": 95.3,
|
| 357 |
+
//"multi-if": 74.8,
|
| 358 |
+
//include: 71.7,
|
| 359 |
+
// "mmmlu-14-languages": 77.9,
|
| 360 |
+
//"mt-aime2024": 73.3,
|
| 361 |
+
//poly//math: 45.8,
|
| 362 |
+
//mlogiqa: 71.1,
|
| 363 |
+
},
|
| 364 |
+
source: "",
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
model: "Qwen3-30B-A3B (Thinking Mode)",
|
| 368 |
+
provider: "Qwen",
|
| 369 |
+
inputPrice: 0,
|
| 370 |
+
outputPrice: 0,
|
| 371 |
+
benchmark: {
|
| 372 |
+
//"mmlu-redux": 89.5,
|
| 373 |
+
gpqa_diamond: 65.8,
|
| 374 |
+
//"c-eval": 86.6,
|
| 375 |
+
//"livebench-2024-11-25": 74.3,
|
| 376 |
+
//"ifeval-strict-prompt": 86.5,
|
| 377 |
+
//"arena-hard": 91.0,
|
| 378 |
+
//"alignbench-v1.1": 8.70,
|
| 379 |
+
//"creative-writing-v3": 79.1,
|
| 380 |
+
//writingbench: 7.70,
|
| 381 |
+
//"math-500": 98.0,
|
| 382 |
+
aime_24: 80.4,
|
| 383 |
+
aime_2025: 70.9,
|
| 384 |
+
//zebralogic: 89.5,
|
| 385 |
+
//autologi: 88.7,
|
| 386 |
+
//"bfcl-v3": 69.1,
|
| 387 |
+
//"livecodebench-v5": 62.6,
|
| 388 |
+
//"codeforces-rating": 1974,
|
| 389 |
+
//"codeforces-percentile": 97.7,
|
| 390 |
+
//"multi-if": 72.2,
|
| 391 |
+
//include: 71.9,
|
| 392 |
+
// "mmmlu-14-languages": 78.4,
|
| 393 |
+
//"mt-aime2024": 73.9,
|
| 394 |
+
//poly//math: 46.1,
|
| 395 |
+
//mlogiqa: 70.1,
|
| 396 |
+
},
|
| 397 |
+
source: "",
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
model: "Qwen3-14B (Non-thinking Mode)",
|
| 401 |
+
provider: "Qwen",
|
| 402 |
+
inputPrice: 0,
|
| 403 |
+
outputPrice: 0,
|
| 404 |
+
benchmark: {
|
| 405 |
+
//"mmlu-redux": 82.0,
|
| 406 |
+
gpqa_diamond: 54.8,
|
| 407 |
+
//"c-eval": 81.0,
|
| 408 |
+
//"livebench-2024-11-25": 59.6,
|
| 409 |
+
//"ifeval-strict-prompt": 84.8,
|
| 410 |
+
//"arena-hard": 86.3,
|
| 411 |
+
//"alignbench-v1.1": 8.52,
|
| 412 |
+
//"creative-writing-v3": 73.1,
|
| 413 |
+
//writingbench: 7.24,
|
| 414 |
+
//"math-500": 90.0,
|
| 415 |
+
aime_24: 31.7,
|
| 416 |
+
aime_2025: 23.3,
|
| 417 |
+
//zebralogic: 33.0,
|
| 418 |
+
//autologi: 82.0,
|
| 419 |
+
//"bfcl-v3": 61.5,
|
| 420 |
+
//"livecodebench-v5": 29.0,
|
| 421 |
+
//"codeforces-rating": 1200,
|
| 422 |
+
//"codeforces-percentile": 58.6,
|
| 423 |
+
//"multi-if": 72.9,
|
| 424 |
+
//include: 67.8,
|
| 425 |
+
// "mmmlu-14-languages": 72.6,
|
| 426 |
+
//"mt-aime2024": 23.2,
|
| 427 |
+
//poly//math: 22.0,
|
| 428 |
+
//mlogiqa: 58.9,
|
| 429 |
+
},
|
| 430 |
+
source: "",
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
model: "Qwen3-30B-A3B (Non-thinking Mode)",
|
| 434 |
+
provider: "Qwen",
|
| 435 |
+
inputPrice: 0,
|
| 436 |
+
outputPrice: 0,
|
| 437 |
+
benchmark: {
|
| 438 |
+
//"mmlu-redux": 84.1,
|
| 439 |
+
gpqa_diamond: 54.8,
|
| 440 |
+
//"c-eval": 82.9,
|
| 441 |
+
//"livebench-2024-11-25": 59.4,
|
| 442 |
+
//"ifeval-strict-prompt": 83.7,
|
| 443 |
+
//"arena-hard": 88.0,
|
| 444 |
+
//"alignbench-v1.1": 8.55,
|
| 445 |
+
//"creative-writing-v3": 68.1,
|
| 446 |
+
//writingbench: 7.22,
|
| 447 |
+
//"math-500": 89.8,
|
| 448 |
+
aime_24: 32.8,
|
| 449 |
+
aime_2025: 21.6,
|
| 450 |
+
//zebralogic: 33.2,
|
| 451 |
+
//autologi: 81.5,
|
| 452 |
+
//"bfcl-v3": 58.6,
|
| 453 |
+
//"livecodebench-v5": 29.8,
|
| 454 |
+
//"codeforces-rating": 1267,
|
| 455 |
+
//"codeforces-percentile": 64.1,
|
| 456 |
+
//"multi-if": 70.8,
|
| 457 |
+
//include: 67.8,
|
| 458 |
+
// "mmmlu-14-languages": 73.8,
|
| 459 |
+
//"mt-aime2024": 24.6,
|
| 460 |
+
//poly//math: 23.3,
|
| 461 |
+
//mlogiqa: 53.3,
|
| 462 |
+
},
|
| 463 |
+
source: "",
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
model: "Qwen3-4B (Thinking Mode)",
|
| 467 |
+
provider: "Qwen",
|
| 468 |
+
inputPrice: 0,
|
| 469 |
+
outputPrice: 0,
|
| 470 |
+
benchmark: {
|
| 471 |
+
//"mmlu-redux": 83.7,
|
| 472 |
+
gpqa_diamond: 55.9,
|
| 473 |
+
//"c-eval": 77.5,
|
| 474 |
+
//"livebench-2024-11-25": 63.6,
|
| 475 |
+
//"ifeval-strict-prompt": 81.9,
|
| 476 |
+
//"arena-hard": 76.6,
|
| 477 |
+
//"alignbench-v1.1": 8.30,
|
| 478 |
+
//"creative-writing-v3": 61.1,
|
| 479 |
+
//writingbench: 7.35,
|
| 480 |
+
//"math-500": 97.0,
|
| 481 |
+
aime_24: 73.8,
|
| 482 |
+
aime_2025: 65.6,
|
| 483 |
+
//zebralogic: 81.0,
|
| 484 |
+
//autologi: 87.9,
|
| 485 |
+
//"bfcl-v3": 65.9,
|
| 486 |
+
//"livecodebench-v5": 54.2,
|
| 487 |
+
//"codeforces-rating": 1671,
|
| 488 |
+
//"codeforces-percentile": 92.8,
|
| 489 |
+
//"multi-if": 66.3,
|
| 490 |
+
//include: 61.8,
|
| 491 |
+
// "mmmlu-14-languages": 69.8,
|
| 492 |
+
//"mt-aime2024": 60.7,
|
| 493 |
+
//poly//math: 40.0,
|
| 494 |
+
//mlogiqa: 65.9,
|
| 495 |
+
},
|
| 496 |
+
source: "",
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
model: "Qwen3-8B (Thinking Mode)",
|
| 500 |
+
provider: "Qwen",
|
| 501 |
+
inputPrice: 0,
|
| 502 |
+
outputPrice: 0,
|
| 503 |
+
benchmark: {
|
| 504 |
+
//"mmlu-redux": 87.5,
|
| 505 |
+
gpqa_diamond: 62.0,
|
| 506 |
+
//"c-eval": 83.4,
|
| 507 |
+
//"livebench-2024-11-25": 67.1,
|
| 508 |
+
//"ifeval-strict-prompt": 85.0,
|
| 509 |
+
//"arena-hard": 85.8,
|
| 510 |
+
//"alignbench-v1.1": 8.46,
|
| 511 |
+
//"creative-writing-v3": 75.0,
|
| 512 |
+
//writingbench: 7.59,
|
| 513 |
+
//"math-500": 97.4,
|
| 514 |
+
aime_24: 76.0,
|
| 515 |
+
aime_2025: 67.3,
|
| 516 |
+
//zebralogic: 84.8,
|
| 517 |
+
//autologi: 89.1,
|
| 518 |
+
//"bfcl-v3": 68.1,
|
| 519 |
+
//"livecodebench-v5": 57.5,
|
| 520 |
+
//"codeforces-rating": 1785,
|
| 521 |
+
//"codeforces-percentile": 95.6,
|
| 522 |
+
//"multi-if": 71.2,
|
| 523 |
+
//include: 67.8,
|
| 524 |
+
// "mmmlu-14-languages": 74.4,
|
| 525 |
+
//"mt-aime2024": 65.4,
|
| 526 |
+
//poly//math: 42.7,
|
| 527 |
+
//mlogiqa: 69.0,
|
| 528 |
+
},
|
| 529 |
+
source: "",
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
model: "Qwen3-4B (Non-thinking Mode)",
|
| 533 |
+
provider: "Qwen",
|
| 534 |
+
inputPrice: 0,
|
| 535 |
+
outputPrice: 0,
|
| 536 |
+
benchmark: {
|
| 537 |
+
//"mmlu-redux": 77.3,
|
| 538 |
+
gpqa_diamond: 41.7,
|
| 539 |
+
//"c-eval": 72.2,
|
| 540 |
+
//"livebench-2024-11-25": 48.4,
|
| 541 |
+
//"ifeval-strict-prompt": 81.2,
|
| 542 |
+
//"arena-hard": 66.2,
|
| 543 |
+
//"alignbench-v1.1": 8.10,
|
| 544 |
+
//"creative-writing-v3": 53.6,
|
| 545 |
+
//writingbench: 6.85,
|
| 546 |
+
//"math-500": 84.8,
|
| 547 |
+
aime_24: 25.0,
|
| 548 |
+
aime_2025: 19.1,
|
| 549 |
+
//zebralogic: 35.2,
|
| 550 |
+
//autologi: 76.3,
|
| 551 |
+
//"bfcl-v3": 57.6,
|
| 552 |
+
//"livecodebench-v5": 21.3,
|
| 553 |
+
//"codeforces-rating": 842,
|
| 554 |
+
//"codeforces-percentile": 33.7,
|
| 555 |
+
//"multi-if": 61.3,
|
| 556 |
+
//include: 53.8,
|
| 557 |
+
// "mmmlu-14-languages": 61.7,
|
| 558 |
+
//"mt-aime2024": 13.9,
|
| 559 |
+
//poly//math: 16.6,
|
| 560 |
+
//mlogiqa: 49.9,
|
| 561 |
+
},
|
| 562 |
+
source: "",
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
model: "Qwen3-8B (Non-thinking Mode)",
|
| 566 |
+
provider: "Qwen",
|
| 567 |
+
inputPrice: 0,
|
| 568 |
+
outputPrice: 0,
|
| 569 |
+
benchmark: {
|
| 570 |
+
//"mmlu-redux": 79.5,
|
| 571 |
+
gpqa_diamond: 39.3,
|
| 572 |
+
//"c-eval": 77.9,
|
| 573 |
+
//"livebench-2024-11-25": 53.5,
|
| 574 |
+
//"ifeval-strict-prompt": 83.0,
|
| 575 |
+
//"arena-hard": 79.6,
|
| 576 |
+
//"alignbench-v1.1": 8.38,
|
| 577 |
+
//"creative-writing-v3": 64.5,
|
| 578 |
+
//writingbench: 7.15,
|
| 579 |
+
//"math-500": 87.4,
|
| 580 |
+
aime_24: 29.1,
|
| 581 |
+
aime_2025: 20.9,
|
| 582 |
+
//zebralogic: 26.7,
|
| 583 |
+
//autologi: 76.5,
|
| 584 |
+
//"bfcl-v3": 60.2,
|
| 585 |
+
//"livecodebench-v5": 22.8,
|
| 586 |
+
//"codeforces-rating": 1110,
|
| 587 |
+
//"codeforces-percentile": 52.4,
|
| 588 |
+
//"multi-if": 69.2,
|
| 589 |
+
//include: 62.5,
|
| 590 |
+
// "mmmlu-14-languages": 66.9,
|
| 591 |
+
//"mt-aime2024": 16.6,
|
| 592 |
+
//poly//math: 18.8,
|
| 593 |
+
//mlogiqa: 51.4,
|
| 594 |
+
},
|
| 595 |
+
source: "",
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
model: "Qwen3-0.6B (Thinking Mode)",
|
| 599 |
+
provider: "Qwen",
|
| 600 |
+
inputPrice: 0,
|
| 601 |
+
outputPrice: 0,
|
| 602 |
+
benchmark: {
|
| 603 |
+
//"mmlu-redux": 55.6,
|
| 604 |
+
gpqa_diamond: 27.9,
|
| 605 |
+
//"c-eval": 50.4,
|
| 606 |
+
//"livebench-2024-11-25": 30.3,
|
| 607 |
+
//"ifeval-strict-prompt": 59.2,
|
| 608 |
+
//"arena-hard": 8.5,
|
| 609 |
+
//"alignbench-v1.1": 6.10,
|
| 610 |
+
//"creative-writing-v3": 30.6,
|
| 611 |
+
//writingbench: 5.61,
|
| 612 |
+
//"math-500": 77.6,
|
| 613 |
+
aime_24: 10.7,
|
| 614 |
+
aime_2025: 15.1,
|
| 615 |
+
//zebralogic: 30.3,
|
| 616 |
+
//autologi: 61.6,
|
| 617 |
+
//"bfcl-v3": 46.4,
|
| 618 |
+
//"livecodebench-v5": 12.3,
|
| 619 |
+
//"multi-if": 36.1,
|
| 620 |
+
//include: 35.9,
|
| 621 |
+
// "mmmlu-14-languages": 43.1,
|
| 622 |
+
//"mt-aime2024": 7.8,
|
| 623 |
+
//poly//math: 11.4,
|
| 624 |
+
//mlogiqa: 40.9,
|
| 625 |
+
},
|
| 626 |
+
source: "",
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
model: "Qwen3-1.7B (Thinking Mode)",
|
| 630 |
+
provider: "Qwen",
|
| 631 |
+
inputPrice: 0,
|
| 632 |
+
outputPrice: 0,
|
| 633 |
+
benchmark: {
|
| 634 |
+
//"mmlu-redux": 73.9,
|
| 635 |
+
gpqa_diamond: 40.1,
|
| 636 |
+
//"c-eval": 68.1,
|
| 637 |
+
//"livebench-2024-11-25": 51.1,
|
| 638 |
+
//"ifeval-strict-prompt": 72.5,
|
| 639 |
+
//"arena-hard": 43.1,
|
| 640 |
+
//"alignbench-v1.1": 7.60,
|
| 641 |
+
//"creative-writing-v3": 48.0,
|
| 642 |
+
//writingbench: 7.02,
|
| 643 |
+
//"math-500": 93.4,
|
| 644 |
+
aime_24: 48.3,
|
| 645 |
+
aime_2025: 36.8,
|
| 646 |
+
//zebralogic: 63.2,
|
| 647 |
+
//autologi: 83.2,
|
| 648 |
+
//"bfcl-v3": 56.6,
|
| 649 |
+
//"livecodebench-v5": 33.2,
|
| 650 |
+
//"multi-if": 51.2,
|
| 651 |
+
//include: 51.8,
|
| 652 |
+
// "mmmlu-14-languages": 59.1,
|
| 653 |
+
//"mt-aime2024": 36.1,
|
| 654 |
+
//poly//math: 25.2,
|
| 655 |
+
//mlogiqa: 56.0,
|
| 656 |
+
},
|
| 657 |
+
source: "",
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
model: "Qwen3-0.6B (Non-thinking Mode)",
|
| 661 |
+
provider: "Qwen",
|
| 662 |
+
inputPrice: 0,
|
| 663 |
+
outputPrice: 0,
|
| 664 |
+
benchmark: {
|
| 665 |
+
//"mmlu-redux": 44.6,
|
| 666 |
+
gpqa_diamond: 22.9,
|
| 667 |
+
//"c-eval": 42.6,
|
| 668 |
+
//"livebench-2024-11-25": 21.8,
|
| 669 |
+
//"ifeval-strict-prompt": 54.5,
|
| 670 |
+
//"arena-hard": 6.5,
|
| 671 |
+
//"alignbench-v1.1": 5.60,
|
| 672 |
+
//"creative-writing-v3": 28.4,
|
| 673 |
+
//writingbench: 5.13,
|
| 674 |
+
//"math-500": 55.2,
|
| 675 |
+
aime_24: 3.4,
|
| 676 |
+
aime_2025: 2.6,
|
| 677 |
+
//zebralogic: 4.2,
|
| 678 |
+
//autologi: 37.4,
|
| 679 |
+
//"bfcl-v3": 44.1,
|
| 680 |
+
//"livecodebench-v5": 3.6,
|
| 681 |
+
//"multi-if": 33.3,
|
| 682 |
+
//include: 34.4,
|
| 683 |
+
// "mmmlu-14-languages": 37.1,
|
| 684 |
+
//"mt-aime2024": 1.5,
|
| 685 |
+
//poly//math: 4.6,
|
| 686 |
+
//mlogiqa: 37.3,
|
| 687 |
+
},
|
| 688 |
+
source: "",
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
model: "Qwen3-1.7B (Non-thinking Mode)",
|
| 692 |
+
provider: "Qwen",
|
| 693 |
+
inputPrice: 0,
|
| 694 |
+
outputPrice: 0,
|
| 695 |
+
benchmark: {
|
| 696 |
+
//"mmlu-redux": 64.4,
|
| 697 |
+
gpqa_diamond: 28.6,
|
| 698 |
+
//"c-eval": 61.0,
|
| 699 |
+
//"livebench-2024-11-25": 35.6,
|
| 700 |
+
//"ifeval-strict-prompt": 68.2,
|
| 701 |
+
//"arena-hard": 36.9,
|
| 702 |
+
//"alignbench-v1.1": 7.20,
|
| 703 |
+
//"creative-writing-v3": 43.6,
|
| 704 |
+
//writingbench: 6.54,
|
| 705 |
+
//"math-500": 73.0,
|
| 706 |
+
aime_24: 13.4,
|
| 707 |
+
aime_2025: 9.8,
|
| 708 |
+
//zebralogic: 12.8,
|
| 709 |
+
//autologi: 59.8,
|
| 710 |
+
//"bfcl-v3": 52.2,
|
| 711 |
+
//"livecodebench-v5": 11.6,
|
| 712 |
+
//"multi-if": 44.7,
|
| 713 |
+
//include: 42.6,
|
| 714 |
+
// "mmmlu-14-languages": 48.3,
|
| 715 |
+
//"mt-aime2024": 4.9,
|
| 716 |
+
//poly//math: 10.3,
|
| 717 |
+
//mlogiqa: 41.1,
|
| 718 |
+
},
|
| 719 |
+
source: "",
|
| 720 |
+
},];
|