Creativity Elicitation on IntElicit 16 scenarios
320Creativity Score (Ocean)IntElicit
Evaluation Results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| IntElicit2026.06 | 320 | 334.33 | 351.33 | 320.33 | 325.33 | 333.67 | 342 | 320.33 | 348 | 312 | 303.67 | 332.33 | 319 | 326.67 | 324 | 302.33 | 325.71 | |
| Deepseek-R12026.06 | 310 | 287 | 343.33 | 294.33 | 330 | 301.67 | 332.67 | 310.33 | 298.33 | 298.33 | 260.33 | 273.67 | 298.33 | 303 | 248 | 285 | 298.4 | |
| GPT-4o2026.06 | 291 | 291.33 | 290 | 318.33 | 323.33 | 325.33 | 268.67 | 317.67 | 347.67 | 293.33 | 258.67 | 304.33 | 295 | 308.67 | 315.33 | 278 | 301.67 | |
| Qwen3-Max2026.06 | 259.33 | 266.67 | 272.67 | 275 | 323.33 | 310.33 | 328.33 | 300.33 | 286.67 | 316 | 282 | 327 | 306.67 | 280.33 | 306 | 267.67 | 294.27 | |
| Llama-3.3-70BParameters=70B2026.06 | 254.33 | 307 | 325.33 | 286.67 | 313.33 | 306.33 | 346 | 315.33 | 261.67 | 300.33 | 287 | 249.33 | 313.67 | 296.67 | 279.33 | 253.33 | 293.48 | |
| Gemini-3-Pro2026.06 | 253.33 | 275.33 | 244.33 | 276 | 271 | 311.67 | 326.67 | 276.67 | 267.67 | 256 | 281 | 316.67 | 293.67 | 295.33 | 282 | 238.33 | 279.1 | |
| Qwen3-235BParameters=235B2026.06 | 245.33 | 330 | 241.67 | 297 | 238.33 | 320 | 302.67 | 255 | 303.67 | 266.67 | 292.67 | 299 | 285 | 290 | 288 | 277 | 283.25 | |
| FPSP2026.06 | 235 | 222.67 | 254.33 | 251.67 | 251.67 | 248.33 | 255 | 288.33 | 306.67 | 236.67 | 240 | 235 | 288.33 | 211 | 238.33 | 220 | 248.94 | |
| CollabLLM2026.06 | 158.67 | 125 | 120 | 153.33 | 116.67 | 148.33 | 106.67 | 135.33 | 181.67 | 136.67 | 156 | 185 | 180 | 139.67 | 166.67 | 135 | 146.54 | |
| Qwen3-8Bversion=base2026.06 | 138.67 | 143.67 | 107 | 148.67 | 153.67 | 113.67 | 183.67 | 163.67 | 193.67 | 137 | 125.33 | 160.33 | 93.67 | 160.33 | 133.67 | 68.67 | 132.86 | |
| Sotopia-RL2026.06 | 115 | 120 | 115 | 116.67 | 133.33 | 126.67 | 111.67 | 213.33 | 201.67 | 191.67 | 140 | 120 | 126.67 | 151.67 | 188.33 | 138.33 | 144.38 |