← Tous les benchmarks
Arene vision
De Wikiprompt, l’encyclopedie libre des prompts
Classement Elo communautaire, agrege chaque jour depuis les duels LMArena. L’arene generale d’abord, puis le detail par categorie.
Derniere mise a jour: 2026-10-11 · 165 modeles
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | claude-fable-5-high | anthropic | 1,324 | 1,317 / 1,331 | 14,175 | Proprietary |
| 2 | claude-opus-5.5-high | anthropic | 1,321 | 1,308 / 1,333 | 2,508 | Proprietary |
| 3 | claude-opus-5-high | anthropic | 1,319 | 1,312 / 1,326 | 16,665 | Proprietary |
| 4 | claude-fable-5.1-max | anthropic | 1,318 | 1,309 / 1,328 | 4,648 | Proprietary |
| 5 | claude-opus-4-7 | anthropic | 1,316 | 1,310 / 1,323 | 23,165 | Proprietary |
| 6 | gemini-3.7-flash-high | google | 1,316 | 1,306 / 1,326 | 4,524 | Proprietary |
| 7 | claude-opus-4-6-high | anthropic | 1,316 | 1,309 / 1,322 | 22,304 | Proprietary |
| 8 | gemini-3.8-flash-high | google | 1,314 | 1,304 / 1,325 | 3,792 | Proprietary |
| 9 | qwen3.8-max | alibaba | 1,314 | 1,306 / 1,321 | 10,017 | Proprietary |
| 10 | claude-opus-4-6 | anthropic | 1,313 | 1,307 / 1,319 | 26,853 | Proprietary |
| 11 | claude-opus-4-7-high | anthropic | 1,313 | 1,306 / 1,320 | 22,733 | Proprietary |
| 12 | gemini-3.5-flash-high | google | 1,310 | 1,303 / 1,317 | 13,103 | Proprietary |
| 13 | muse-spark-1.3-max | meta | 1,309 | 1,300 / 1,319 | 4,550 | Proprietary |
| 14 | gemini-3.5-flash-medium | google | 1,309 | 1,302 / 1,316 | 13,180 | Proprietary |
| 15 | muse-spark | meta | 1,306 | 1,297 / 1,315 | 5,872 | Proprietary |
| 16 | gemini-3-pro | google | 1,305 | 1,297 / 1,312 | 13,639 | Proprietary |
| 17 | muse-spark-1.2 (xHigh) | meta | 1,305 | 1,290 / 1,319 | 1,954 | Proprietary |
| 18 | gpt-5.4-high | openai | 1,303 | 1,297 / 1,309 | 29,881 | Proprietary |
| 19 | muse-spark-1.3 (xHigh) | meta | 1,301 | 1,290 / 1,311 | 4,077 | Proprietary |
| 20 | gemini-3.6-flash-high | google | 1,298 | 1,290 / 1,306 | 8,127 | Proprietary |
| 21 | gpt-5.5 | openai | 1,297 | 1,291 / 1,302 | 27,993 | Proprietary |
| 22 | gemini-3.1-pro-preview | google | 1,296 | 1,291 / 1,301 | 46,320 | Proprietary |
| 23 | glm-5.3-flash | zai | 1,296 | 1,289 / 1,303 | 11,157 | MIT |
| 24 | claude-opus-4-8-high | anthropic | 1,294 | 1,288 / 1,301 | 18,341 | Proprietary |
| 25 | muse-spark-1.1 | meta | 1,293 | 1,286 / 1,300 | 11,994 | Proprietary |
| 26 | gpt-5.5-high | openai | 1,292 | 1,286 / 1,298 | 26,281 | Proprietary |
| 27 | gpt-5.4 | openai | 1,292 | 1,286 / 1,299 | 22,832 | Proprietary |
| 28 | claude-sonnet-5.5-xhigh | anthropic | 1,289 | 1,275 / 1,302 | 2,068 | Proprietary |
| 29 | claude-opus-4-8 | anthropic | 1,289 | 1,282 / 1,295 | 18,852 | Proprietary |
| 30 | gpt-6.1-sol-max | openai | 1,288 | 1,274 / 1,303 | 1,813 | Proprietary |
| 31 | grok-4.5 | xai | 1,288 | 1,281 / 1,295 | 11,764 | Proprietary |
| 32 | gemini-3-flash | google | 1,285 | 1,280 / 1,290 | 39,145 | Proprietary |
| 33 | kimi-k2.6 | moonshot | 1,283 | 1,276 / 1,290 | 16,379 | Modified MIT |
| 34 | claude-sonnet-4-6 | anthropic | 1,282 | 1,276 / 1,289 | 27,422 | Proprietary |
| 35 | gpt-5.6-sol-xhigh | openai | 1,281 | 1,274 / 1,289 | 10,907 | Proprietary |
| 36 | gpt-6-astra-max | openai | 1,281 | 1,271 / 1,292 | 3,590 | Proprietary |
| 37 | qwen3.7-plus | alibaba | 1,279 | 1,272 / 1,286 | 13,636 | Proprietary |
| 38 | gemma-4-31b | google | 1,277 | 1,271 / 1,283 | 39,669 | Apache 2.0 |
| 39 | deepseek-v4.1-flash-max | deepseek | 1,277 | 1,266 / 1,287 | 3,559 | MIT |
| 40 | dola-seed-2.0-pro | bytedance | 1,274 | 1,267 / 1,281 | 10,982 | Proprietary |
| 41 | claude-sonnet-5-high | anthropic | 1,274 | 1,267 / 1,281 | 13,503 | Proprietary |
| 42 | qwen3.8-27b | alibaba | 1,271 | 1,263 / 1,280 | 7,013 | Apache 2.0 |
| 43 | gpt-5.6-terra-xhigh | openai | 1,271 | 1,264 / 1,278 | 11,020 | Proprietary |
| 44 | kimi-k2.5-thinking | moonshot | 1,269 | 1,263 / 1,274 | 28,297 | Modified MIT |
| 45 | gemini-3.5-flash-lite | google | 1,268 | 1,260 / 1,276 | 8,381 | Proprietary |
| 46 | gpt-5.2-chat-latest-20260210 | openai | 1,268 | 1,261 / 1,274 | 16,480 | Proprietary |
| 47 | Step 5 Preview | stepfun | 1,267 | 1,249 / 1,286 | 1,088 | Proprietary |
| 48 | gemini-3-flash (thinking-minimal) | google | 1,266 | 1,260 / 1,271 | 37,172 | Proprietary |
| 49 | glm-5v-turbo | zai | 1,264 | 1,259 / 1,270 | 42,182 | Proprietary |
| 50 | mimo-v2.6-pro | xiaomi | 1,264 | 1,249 / 1,279 | 1,778 | MIT |
| 51 | gemini-2.5-pro | google | 1,263 | 1,259 / 1,268 | 88,805 | Proprietary |
| 52 | grok-4.6-high | xai | 1,263 | 1,254 / 1,272 | 6,495 | Proprietary |
| 53 | grok-4.20-beta-0309-reasoning | xai | 1,263 | 1,257 / 1,269 | 26,828 | Proprietary |
| 54 | qwen3.5-397b-a17b | alibaba | 1,263 | 1,257 / 1,268 | 32,058 | Apache 2.0 |
| 55 | gemma-4-26b-a4b | google | 1,260 | 1,253 / 1,266 | 23,943 | Apache 2.0 |
| 56 | mimo-v2.6-flash | xiaomi | 1,259 | 1,247 / 1,271 | 2,908 | MIT |
| 57 | grok-4.20-multi-agent-beta-0309 | xai | 1,259 | 1,253 / 1,265 | 24,543 | Proprietary |
| 58 | gpt-5.6-luna-xhigh | openai | 1,258 | 1,251 / 1,266 | 11,086 | Proprietary |
| 59 | kimi-k2.5-instant | moonshot | 1,253 | 1,243 / 1,264 | 4,114 | Modified MIT |
| 60 | minimax-m3 | minimax | 1,253 | 1,247 / 1,260 | 19,026 | MiniMax Community License |
| 61 | gemini-2.5-flash-preview-09-2025 | google | 1,253 | 1,243 / 1,263 | 4,804 | Proprietary |
| 62 | gpt-5.5-instant | openai | 1,250 | 1,241 / 1,259 | 7,603 | Proprietary |
| 63 | gpt-5.1-high | openai | 1,250 | 1,242 / 1,258 | 9,861 | Proprietary |
| 64 | ernie-5.0-preview-1220 | baidu | 1,248 | 1,237 / 1,260 | 3,351 | Proprietary |
| 65 | mimo-v2.5 | xiaomi | 1,247 | 1,241 / 1,253 | 28,794 | MIT |
| 66 | qwen3-vl-235b-a22b-instruct | alibaba | 1,247 | 1,240 / 1,254 | 12,751 | Apache 2.0 |
| 67 | gpt-5.2-high | openai | 1,246 | 1,240 / 1,252 | 19,041 | Proprietary |
| 68 | gpt-5.4-mini-high | openai | 1,245 | 1,239 / 1,251 | 25,733 | Proprietary |
| 69 | gpt-6-sol-max | openai | 1,245 | 1,232 / 1,257 | 2,657 | Proprietary |
| 70 | qwen3.5-122b-a10b | alibaba | 1,245 | 1,238 / 1,251 | 13,241 | Apache 2.0 |
| 71 | chatgpt-4o-latest-20250326 | openai | 1,243 | 1,238 / 1,249 | 23,433 | Proprietary |
| 72 | qwen3.5-27b | alibaba | 1,241 | 1,235 / 1,246 | 29,644 | Apache 2.0 |
| 73 | gemini-3.1-flash-lite-preview | google | 1,240 | 1,234 / 1,246 | 27,683 | Proprietary |
| 74 | gemini-2.5-flash | google | 1,235 | 1,231 / 1,240 | 60,112 | Proprietary |
| 75 | Inkling Small | thinky | 1,235 | 1,227 / 1,244 | 7,472 | Apache 2.0 |
| 76 | gpt-5.1 | openai | 1,235 | 1,227 / 1,242 | 10,818 | Proprietary |
| 77 | gpt-5-chat | openai | 1,232 | 1,225 / 1,239 | 39,920 | Proprietary |
| 78 | grok-4.3 | xai | 1,229 | 1,223 / 1,235 | 27,037 | Proprietary |
| 79 | gpt-5.2 | openai | 1,229 | 1,223 / 1,235 | 20,127 | Proprietary |
| 80 | grok-4.7-xhigh | xai | 1,228 | 1,216 / 1,240 | 2,942 | Proprietary |
| 81 | mimo-v2-omni | xiaomi | 1,228 | 1,220 / 1,235 | 10,663 | Proprietary |
| 82 | mistral-medium-3.5 | mistral | 1,223 | 1,214 / 1,233 | 5,375 | Modified MIT |
| 83 | mistral-large-3 | mistral | 1,221 | 1,213 / 1,229 | 8,643 | Apache 2.0 |
| 84 | gpt-6-luna-max | openai | 1,217 | 1,205 / 1,229 | 2,833 | Proprietary |
| 85 | o3-2025-04-16 | openai | 1,214 | 1,208 / 1,221 | 45,599 | Proprietary |
| 86 | qwen-vl-max-2025-08-13 | alibaba | 1,213 | 1,201 / 1,225 | 3,171 | Proprietary |
| 87 | gpt-4.1-2025-04-14 | openai | 1,211 | 1,204 / 1,217 | 41,017 | Proprietary |
| 88 | grok-4-0709 | xai | 1,210 | 1,203 / 1,217 | 30,191 | Proprietary |
| 89 | gpt-5-high | openai | 1,208 | 1,201 / 1,215 | 34,470 | Proprietary |
| 90 | qwen3-vl-235b-a22b-thinking | alibaba | 1,207 | 1,194 / 1,219 | 2,386 | Apache 2.0 |
| 91 | gpt-5-mini-high | openai | 1,202 | 1,194 / 1,210 | 28,959 | Proprietary |
| 92 | grok-4-1-fast-reasoning | xai | 1,201 | 1,194 / 1,208 | 13,373 | Proprietary |
| 93 | gemini-2.5-flash-lite-preview-09-2025-no-thinking | google | 1,198 | 1,189 / 1,208 | 4,870 | Proprietary |
| 94 | gpt-5.4-nano-high | openai | 1,196 | 1,190 / 1,202 | 25,650 | Proprietary |
| 95 | gpt-4.5-preview-2025-02-27 | openai | 1,195 | 1,183 / 1,207 | 2,925 | Proprietary |
| 96 | o4-mini-2025-04-16 | openai | 1,194 | 1,187 / 1,201 | 41,341 | Proprietary |
| 97 | claude-opus-4-20250514-thinking-16k | anthropic | 1,192 | 1,176 / 1,208 | 1,289 | Proprietary |
| 98 | claude-sonnet-4-20250514-thinking-32k | anthropic | 1,191 | 1,174 / 1,208 | 1,145 | Proprietary |
| 99 | gemini-2.5-flash-lite-preview-06-17-thinking | google | 1,187 | 1,180 / 1,195 | 35,932 | Proprietary |
| 100 | step-1o-turbo-202506 | stepfun | 1,186 | 1,172 / 1,200 | 1,899 | Proprietary |
Par categorie
Ocr
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | claude-fable-5-high | anthropic | 1,336 | 1,329 / 1,344 | 10,128 | Proprietary |
| 2 | gemini-3.8-flash-high | google | 1,334 | 1,322 / 1,347 | 2,570 | Proprietary |
| 3 | claude-opus-5-high | anthropic | 1,329 | 1,322 / 1,336 | 11,483 | Proprietary |
| 4 | claude-opus-5.5-high | anthropic | 1,327 | 1,312 / 1,341 | 1,777 | Proprietary |
| 5 | claude-opus-4-6 | anthropic | 1,327 | 1,320 / 1,333 | 19,427 | Proprietary |
| 6 | claude-fable-5.1-max | anthropic | 1,326 | 1,316 / 1,337 | 3,190 | Proprietary |
| 7 | claude-opus-4-7 | anthropic | 1,326 | 1,319 / 1,333 | 16,764 | Proprietary |
| 8 | claude-opus-4-6-high | anthropic | 1,326 | 1,319 / 1,332 | 15,929 | Proprietary |
| 9 | gemini-3.7-flash-high | google | 1,324 | 1,313 / 1,335 | 3,080 | Proprietary |
| 10 | qwen3.8-max | alibaba | 1,323 | 1,315 / 1,331 | 6,954 | Proprietary |
| 11 | claude-opus-4-7-high | anthropic | 1,320 | 1,314 / 1,327 | 16,375 | Proprietary |
| 12 | muse-spark-1.3-max | meta | 1,318 | 1,307 / 1,330 | 3,124 | Proprietary |
| 13 | gemini-3.5-flash-medium | google | 1,318 | 1,310 / 1,325 | 9,126 | Proprietary |
| 14 | gemini-3.5-flash-high | google | 1,313 | 1,306 / 1,320 | 9,077 | Proprietary |
| 15 | muse-spark-1.2 (xHigh) | meta | 1,313 | 1,296 / 1,330 | 1,348 | Proprietary |
English
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | claude-fable-5-high | anthropic | 1,324 | 1,314 / 1,334 | 5,721 | Proprietary |
| 2 | claude-opus-4-6-high | anthropic | 1,324 | 1,315 / 1,332 | 9,251 | Proprietary |
| 3 | claude-opus-4-7 | anthropic | 1,322 | 1,313 / 1,330 | 9,843 | Proprietary |
| 4 | claude-opus-4-7-high | anthropic | 1,320 | 1,311 / 1,329 | 9,702 | Proprietary |
| 5 | claude-opus-4-6 | anthropic | 1,319 | 1,311 / 1,328 | 11,327 | Proprietary |
| 6 | claude-opus-5.5-high | anthropic | 1,319 | 1,297 / 1,340 | 818 | Proprietary |
| 7 | claude-opus-5-high | anthropic | 1,315 | 1,306 / 1,325 | 5,880 | Proprietary |
| 8 | gemini-3.8-flash-high | google | 1,313 | 1,295 / 1,330 | 1,275 | Proprietary |
| 9 | claude-fable-5.1-max | anthropic | 1,311 | 1,296 / 1,326 | 1,686 | Proprietary |
| 10 | qwen3.8-max | alibaba | 1,310 | 1,299 / 1,322 | 3,299 | Proprietary |
| 11 | gemini-3.7-flash-high | google | 1,308 | 1,292 / 1,324 | 1,554 | Proprietary |
| 12 | gemini-3.5-flash-high | google | 1,305 | 1,295 / 1,315 | 4,776 | Proprietary |
| 13 | muse-spark | meta | 1,304 | 1,291 / 1,317 | 2,429 | Proprietary |
| 14 | gpt-5.4-high | openai | 1,301 | 1,293 / 1,310 | 11,832 | Proprietary |
| 15 | gemini-3.5-flash-medium | google | 1,301 | 1,291 / 1,311 | 4,741 | Proprietary |
Diagram
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | claude-fable-5-high | anthropic | 1,355 | 1,345 / 1,366 | 3,815 | Proprietary |
| 2 | claude-opus-5-high | anthropic | 1,348 | 1,339 / 1,358 | 4,254 | Proprietary |
| 3 | claude-fable-5.1-max | anthropic | 1,346 | 1,328 / 1,364 | 1,100 | Proprietary |
| 4 | gemini-3.8-flash-high | google | 1,345 | 1,325 / 1,364 | 979 | Proprietary |
| 5 | claude-opus-4-6 | anthropic | 1,340 | 1,331 / 1,349 | 7,260 | Proprietary |
| 6 | claude-opus-5.5-high | anthropic | 1,339 | 1,314 / 1,364 | 589 | Proprietary |
| 7 | claude-opus-4-7-high | anthropic | 1,336 | 1,327 / 1,345 | 6,251 | Proprietary |
| 8 | claude-opus-4-7 | anthropic | 1,335 | 1,326 / 1,344 | 6,424 | Proprietary |
| 9 | claude-opus-4-6-high | anthropic | 1,332 | 1,323 / 1,341 | 5,999 | Proprietary |
| 10 | muse-spark-1.3-max | meta | 1,330 | 1,312 / 1,348 | 1,139 | Proprietary |
| 11 | gemini-3.7-flash-high | google | 1,329 | 1,311 / 1,347 | 1,167 | Proprietary |
| 12 | claude-sonnet-5.5-xhigh | anthropic | 1,328 | 1,301 / 1,354 | 514 | Proprietary |
| 13 | gpt-5.4-high | openai | 1,327 | 1,319 / 1,335 | 8,005 | Proprietary |
| 14 | gpt-5.5 | openai | 1,325 | 1,317 / 1,334 | 7,612 | Proprietary |
| 15 | gemini-3.5-flash-medium | google | 1,325 | 1,315 / 1,336 | 3,398 | Proprietary |
Homework
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | claude-opus-5.5-high | anthropic | 1,359 | 1,326 / 1,392 | 322 | Proprietary |
| 2 | claude-fable-5-high | anthropic | 1,357 | 1,342 / 1,372 | 1,684 | Proprietary |
| 3 | gpt-6.1-sol-max | openai | 1,352 | 1,316 / 1,388 | 275 | Proprietary |
| 4 | gemini-3.8-flash-high | google | 1,351 | 1,325 / 1,376 | 526 | Proprietary |
| 5 | claude-fable-5.1-max | anthropic | 1,346 | 1,323 / 1,368 | 690 | Proprietary |
| 6 | qwen3.8-max | alibaba | 1,343 | 1,323 / 1,362 | 945 | Proprietary |
| 7 | claude-opus-5-high | anthropic | 1,342 | 1,327 / 1,357 | 1,740 | Proprietary |
| 8 | gpt-6-astra-max | openai | 1,342 | 1,315 / 1,368 | 480 | Proprietary |
| 9 | gpt-5.4-high | openai | 1,338 | 1,327 / 1,348 | 3,876 | Proprietary |
| 10 | claude-opus-4-7-high | anthropic | 1,337 | 1,326 / 1,349 | 3,091 | Proprietary |
| 11 | claude-opus-4-8-high | anthropic | 1,337 | 1,323 / 1,350 | 2,080 | Proprietary |
| 12 | claude-opus-4-6-high | anthropic | 1,336 | 1,325 / 1,348 | 2,849 | Proprietary |
| 13 | claude-opus-4-7 | anthropic | 1,334 | 1,322 / 1,345 | 3,177 | Proprietary |
| 14 | gpt-5.5-high | openai | 1,333 | 1,322 / 1,344 | 3,420 | Proprietary |
| 15 | gemini-3.7-flash-high | google | 1,332 | 1,307 / 1,356 | 543 | Proprietary |
Chinese
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 2 | claude-opus-5-high | anthropic | 1,404 | 1,383 / 1,425 | 985 | Proprietary |
| 5 | gemini-3.5-flash-high | google | 1,378 | 1,356 / 1,401 | 820 | Proprietary |
| 7 | gemini-3.5-flash-medium | google | 1,376 | 1,354 / 1,399 | 777 | Proprietary |
| 8 | claude-fable-5-high | anthropic | 1,373 | 1,350 / 1,396 | 765 | Proprietary |
| 9 | claude-opus-4-6 | anthropic | 1,370 | 1,353 / 1,387 | 1,685 | Proprietary |
| 10 | claude-opus-4-7 | anthropic | 1,370 | 1,353 / 1,388 | 1,505 | Proprietary |
| 11 | gemini-3-pro | google | 1,370 | 1,353 / 1,387 | 1,687 | Proprietary |
| 12 | glm-5.3-flash | zai | 1,367 | 1,339 / 1,395 | 453 | MIT |
| 13 | claude-opus-4-6-high | anthropic | 1,366 | 1,349 / 1,384 | 1,488 | Proprietary |
| 14 | gemini-3.1-pro-preview | google | 1,365 | 1,351 / 1,378 | 3,137 | Proprietary |
| 17 | qwen3.8-max | alibaba | 1,361 | 1,335 / 1,387 | 546 | Proprietary |
| 18 | gpt-5.5 | openai | 1,360 | 1,343 / 1,377 | 1,741 | Proprietary |
| 19 | gpt-5.5-high | openai | 1,358 | 1,340 / 1,375 | 1,553 | Proprietary |
| 20 | claude-opus-4-7-high | anthropic | 1,355 | 1,336 / 1,373 | 1,389 | Proprietary |
| 21 | gpt-5.4-high | openai | 1,353 | 1,337 / 1,370 | 1,807 | Proprietary |
Creative writing vision
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | gemini-3-pro | google | 1,341 | 1,322 / 1,359 | 1,102 | Proprietary |
| 2 | claude-fable-5-high | anthropic | 1,339 | 1,320 / 1,358 | 1,115 | Proprietary |
| 4 | claude-opus-4-6-high | anthropic | 1,332 | 1,315 / 1,349 | 1,405 | Proprietary |
| 5 | claude-fable-5.1-max | anthropic | 1,329 | 1,300 / 1,359 | 476 | Proprietary |
| 6 | claude-opus-4-7-high | anthropic | 1,325 | 1,309 / 1,341 | 1,448 | Proprietary |
| 7 | gemini-3.1-pro-preview | google | 1,324 | 1,313 / 1,335 | 3,200 | Proprietary |
| 8 | muse-spark | meta | 1,324 | 1,291 / 1,357 | 345 | Proprietary |
| 9 | claude-opus-4-7 | anthropic | 1,320 | 1,303 / 1,337 | 1,391 | Proprietary |
| 10 | claude-opus-4-6 | anthropic | 1,319 | 1,304 / 1,335 | 1,731 | Proprietary |
| 11 | gemini-3-flash | google | 1,315 | 1,303 / 1,327 | 2,983 | Proprietary |
| 12 | gemini-3.7-flash-high | google | 1,314 | 1,284 / 1,344 | 427 | Proprietary |
| 13 | qwen3.8-max | alibaba | 1,314 | 1,292 / 1,336 | 748 | Proprietary |
| 14 | claude-opus-5-high | anthropic | 1,312 | 1,296 / 1,328 | 1,526 | Proprietary |
| 15 | gemini-3.5-flash-medium | google | 1,305 | 1,286 / 1,324 | 1,048 | Proprietary |
| 16 | gpt-5.5-high | openai | 1,302 | 1,288 / 1,316 | 1,952 | Proprietary |
Humor
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 2 | claude-fable-5-high | anthropic | 1,341 | 1,316 / 1,367 | 567 | Proprietary |
| 3 | gemini-3-pro | google | 1,339 | 1,314 / 1,363 | 613 | Proprietary |
| 5 | gemini-3.1-pro-preview | google | 1,323 | 1,308 / 1,337 | 1,865 | Proprietary |
| 6 | gemini-3.5-flash-medium | google | 1,322 | 1,296 / 1,349 | 533 | Proprietary |
| 7 | gemini-3.5-flash-high | google | 1,317 | 1,291 / 1,343 | 553 | Proprietary |
| 8 | claude-opus-4-6 | anthropic | 1,313 | 1,294 / 1,333 | 1,025 | Proprietary |
| 9 | claude-opus-4-6-high | anthropic | 1,313 | 1,292 / 1,334 | 869 | Proprietary |
| 10 | claude-opus-4-7-high | anthropic | 1,308 | 1,287 / 1,329 | 890 | Proprietary |
| 12 | qwen3.8-max | alibaba | 1,305 | 1,276 / 1,335 | 429 | Proprietary |
| 13 | claude-opus-4-7 | anthropic | 1,305 | 1,285 / 1,325 | 897 | Proprietary |
| 15 | claude-opus-5-high | anthropic | 1,296 | 1,275 / 1,317 | 841 | Proprietary |
| 16 | gpt-5.5-high | openai | 1,293 | 1,274 / 1,312 | 1,044 | Proprietary |
| 17 | gemini-3-flash | google | 1,291 | 1,275 / 1,307 | 1,441 | Proprietary |
| 18 | gemini-3.6-flash-high | google | 1,289 | 1,259 / 1,319 | 398 | Proprietary |
| 19 | gpt-5.4-high | openai | 1,285 | 1,267 / 1,304 | 1,103 | Proprietary |
Creative writing
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 1 | gemini-3-pro | google | 1,391 | 1,368 / 1,413 | 766 | Proprietary |
| 4 | gpt-5.1 | openai | 1,291 | 1,262 / 1,321 | 411 | Proprietary |
| 5 | gemini-2.5-flash-preview-09-2025 | google | 1,289 | 1,264 / 1,313 | 555 | Proprietary |
| 6 | gpt-5.1-high | openai | 1,282 | 1,252 / 1,313 | 385 | Proprietary |
| 7 | gemini-2.5-pro | google | 1,277 | 1,264 / 1,291 | 2,418 | Proprietary |
| 8 | grok-4-0709 | xai | 1,265 | 1,249 / 1,282 | 1,461 | Proprietary |
| 10 | gemini-2.5-flash | google | 1,253 | 1,238 / 1,268 | 1,745 | Proprietary |
| 11 | chatgpt-4o-latest-20250326 | openai | 1,248 | 1,230 / 1,266 | 1,047 | Proprietary |
| 12 | gpt-5-chat | openai | 1,239 | 1,224 / 1,255 | 1,518 | Proprietary |
| 14 | qwen3-vl-235b-a22b-instruct | alibaba | 1,225 | 1,203 / 1,247 | 690 | Apache 2.0 |
| 15 | mistral-medium-2508 | mistral | 1,223 | 1,207 / 1,239 | 1,365 | Proprietary |
| 16 | gpt-4.1-2025-04-14 | openai | 1,223 | 1,207 / 1,239 | 1,432 | Proprietary |
| 17 | gemini-2.5-flash-lite-preview-09-2025-no-thinking | google | 1,220 | 1,196 / 1,244 | 565 | Proprietary |
| 18 | gemini-2.0-flash-001 | google | 1,205 | 1,172 / 1,239 | 292 | Proprietary |
| 19 | o3-2025-04-16 | openai | 1,197 | 1,183 / 1,211 | 1,880 | Proprietary |
Entity recognition
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 2 | gemini-3-flash | google | 1,335 | 1,305 / 1,364 | 368 | Proprietary |
| 3 | gemini-3.1-pro-preview | google | 1,329 | 1,300 / 1,358 | 387 | Proprietary |
| 4 | gemini-3-flash (thinking-minimal) | google | 1,310 | 1,280 / 1,340 | 323 | Proprietary |
| 6 | grok-4-0709 | xai | 1,288 | 1,254 / 1,323 | 332 | Proprietary |
| 7 | kimi-k2.5-thinking | moonshot | 1,284 | 1,252 / 1,316 | 275 | Modified MIT |
| 8 | gemini-2.5-pro | google | 1,283 | 1,261 / 1,305 | 917 | Proprietary |
| 15 | gpt-5-high | openai | 1,262 | 1,232 / 1,293 | 432 | Proprietary |
| 16 | gemini-2.5-flash | google | 1,251 | 1,228 / 1,275 | 628 | Proprietary |
| 20 | chatgpt-4o-latest-20250326 | openai | 1,245 | 1,213 / 1,277 | 295 | Proprietary |
| 24 | o3-2025-04-16 | openai | 1,234 | 1,204 / 1,264 | 495 | Proprietary |
| 28 | gpt-5-mini-high | openai | 1,226 | 1,190 / 1,262 | 282 | Proprietary |
| 30 | gemma-4-31b | google | 1,224 | 1,195 / 1,252 | 357 | Apache 2.0 |
| 32 | o4-mini-2025-04-16 | openai | 1,219 | 1,187 / 1,251 | 389 | Proprietary |
| 33 | gpt-5-chat | openai | 1,219 | 1,186 / 1,252 | 377 | Proprietary |
| 36 | gpt-4.1-2025-04-14 | openai | 1,208 | 1,175 / 1,240 | 392 | Proprietary |
Captioning
| Rang | Modele | Organisation | Score Elo | IC 95% | Votes | Licence |
|---|
| 3 | gemini-2.5-pro | google | 1,304 | 1,281 / 1,326 | 795 | Proprietary |
| 7 | gemini-2.5-flash | google | 1,277 | 1,253 / 1,302 | 581 | Proprietary |
| 13 | grok-4-0709 | xai | 1,245 | 1,211 / 1,279 | 351 | Proprietary |
| 18 | gpt-5-mini-high | openai | 1,217 | 1,180 / 1,253 | 283 | Proprietary |
| 19 | gpt-5-chat | openai | 1,212 | 1,180 / 1,243 | 375 | Proprietary |
| 20 | o3-2025-04-16 | openai | 1,210 | 1,182 / 1,237 | 541 | Proprietary |
| 21 | gpt-4.1-2025-04-14 | openai | 1,207 | 1,176 / 1,238 | 422 | Proprietary |
| 22 | o4-mini-2025-04-16 | openai | 1,203 | 1,173 / 1,233 | 424 | Proprietary |
| 23 | gpt-5-high | openai | 1,203 | 1,171 / 1,235 | 357 | Proprietary |
| 24 | gemini-2.5-flash-lite-preview-06-17-thinking | google | 1,185 | 1,153 / 1,216 | 385 | Proprietary |
| 26 | gpt-4.1-mini-2025-04-14 | openai | 1,173 | 1,141 / 1,206 | 395 | Proprietary |
| 31 | mistral-medium-2508 | mistral | 1,146 | 1,115 / 1,176 | 404 | Proprietary |
Sources et methodologie
Les classements sont agreges depuis des evaluations communautaires ouvertes. Les scores Elo, intervalles de confiance et votes proviennent de LMArena (duels de modeles votes par la communaute, publies en dataset ouvert). Les prix et metadonnees de contexte proviennent de l’API publique OpenRouter. Wikiprompt prend un instantane quotidien et preserve l’historique ; nous ne menons aucune evaluation proprietaire.
- LMArena leaderboard dataset (Hugging Face)
- LMArena leaderboard