← Tous les instantanesVoir le classement en direct
Instantane des benchmarks: 2026-09-08
De Wikiprompt, l’encyclopedie libre des prompts
Photo figee des classements a cette date. Le classement en direct est sur /benchmarks.
← 2026-09-072026-09-09 →
Arene texte
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 2 | claude-opus-5-high | anthropic | 1,505 | 35,174 |
| 4 | claude-opus-4-6-high | anthropic | 1,503 | 72,099 |
| 5 | claude-opus-4-6 | anthropic | 1,498 | 76,015 |
| 7 | claude-fable-5 | anthropic | 1,494 | 27,189 |
| 9 | claude-opus-4-7-high | anthropic | 1,490 | 60,103 |
| 11 | gemini-3.5-flash-high | google | 1,484 | 34,180 |
| 12 | claude-opus-4-7 | anthropic | 1,483 | 61,238 |
| 13 | gemini-3.1-pro-preview | google | 1,480 | 102,999 |
| 15 | gemini-3-pro | google | 1,479 | 40,668 |
| 16 | muse-spark-1.1 | meta | 1,479 | 24,064 |
| 17 | gemini-3.5-flash-medium | google | 1,477 | 32,573 |
| 18 | gemini-3.6-flash-high | google | 1,476 | 22,286 |
| 23 | qwen3.5-max-preview | alibaba | 1,471 | 21,485 |
| 24 | gpt-5.5-high | openai | 1,471 | 63,547 |
| 26 | gpt-5.4-high | openai | 1,470 | 60,624 |
Arene developpement web
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | gpt-6-astra-max | openai | 1,797 | 1,199 |
| 2 | claude-fable-5.1-max | anthropic | 1,762 | 2,275 |
| 3 | claude-opus-5-max | anthropic | 1,688 | 10,904 |
| 4 | qwen3.8-max-0902 | alibaba | 1,686 | 1,868 |
| 5 | kimi-k3-max | moonshot | 1,674 | 4,546 |
| 6 | qwen3.8-max | alibaba | 1,670 | 3,223 |
| 7 | claude-opus-5-high | anthropic | 1,661 | 10,928 |
| 8 | claude-fable-5 | anthropic | 1,629 | 9,356 |
| 9 | qwen3.8-flash-next | alibaba | 1,626 | 2,158 |
| 10 | grok-4.6-high | xai | 1,625 | 3,487 |
| 11 | muse-spark-1.3 (xHigh) | meta | 1,622 | 1,274 |
| 12 | hy4-preview | tencent | 1,621 | 1,661 |
| 13 | gpt-5.6-sol-xhigh (codex-harness) | openai | 1,617 | 11,014 |
| 14 | glm-5.3-max | zai | 1,609 | 2,930 |
| 15 | glm-5.3-flash | zai | 1,605 | 1,961 |
Arene vision
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | claude-fable-5 | anthropic | 1,329 | 10,002 |
| 2 | claude-opus-5-high | anthropic | 1,322 | 8,271 |
| 3 | claude-opus-4-7 | anthropic | 1,317 | 21,457 |
| 4 | claude-opus-4-7-high | anthropic | 1,316 | 21,137 |
| 5 | claude-opus-4-6-high | anthropic | 1,315 | 20,883 |
| 6 | qwen3.8-max | alibaba | 1,313 | 7,244 |
| 7 | claude-opus-4-6 | anthropic | 1,311 | 25,210 |
| 8 | gemini-3.5-flash-high | google | 1,311 | 8,259 |
| 9 | muse-spark | meta | 1,306 | 5,585 |
| 10 | gemini-3.5-flash-medium | google | 1,306 | 8,261 |
| 11 | gemini-3-pro | google | 1,304 | 13,019 |
| 12 | muse-spark-1.2 (xHigh) | meta | 1,304 | 1,844 |
| 13 | gemini-3.6-flash-high | google | 1,302 | 3,816 |
| 14 | gpt-5.4-high | openai | 1,298 | 23,263 |
| 15 | glm-5.3-flash | zai | 1,296 | 1,389 |
Arene texte vers image
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | gpt-image-2 (medium) | openai | 1,382 | 77,830 |
| 2 | mai-image-2.6 | microsoft-ai | 1,332 | 10,086 |
| 3 | grok-imagine-image-2.0 (low) | xai | 1,315 | 2,682 |
| 4 | reve-2.1 | reve | 1,301 | 7,576 |
| 5 | muse-image | meta | 1,279 | 24,856 |
| 6 | reve-2.0 | reve | 1,270 | 14,636 |
| 7 | gemini-3.1-flash-image (nano-banana-2) [web-search] | google | 1,261 | 40,649 |
| 8 | seedream-5.0-pro | bytedance | 1,258 | 59,484 |
| 9 | qwen-image-3.0-pro | alibaba | 1,254 | 10,923 |
| 10 | mai-image-2.5 | microsoft-ai | 1,254 | 57,295 |
| 11 | gemini-3.1-flash-lite-image (nano-banana-2-lite) | google | 1,250 | 16,389 |
| 12 | gemini-3-pro-image-2k (nano-banana-pro) | google | 1,246 | 150,932 |
| 13 | gpt-image-1.5-high-fidelity | openai | 1,239 | 150,845 |
| 14 | gemini-3-pro-image-preview (nano-banana-pro) | google | 1,232 | 82,744 |
| 15 | ideogram-4.0-quality | ideogram | 1,204 | 40,898 |
Arene edition d’image
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | gpt-image-2 (medium) | openai | 1,461 | 228,827 |
| 2 | mai-image-2.6 | microsoft-ai | 1,439 | 5,086 |
| 3 | grok-imagine-image-2.0 (low) | xai | 1,439 | 5,941 |
| 4 | muse-image | meta | 1,403 | 76,663 |
| 5 | mai-image-2.5 | microsoft-ai | 1,400 | 174,732 |
| 6 | seedream-5.0-pro | bytedance | 1,394 | 165,349 |
| 7 | chatgpt-image-latest-high-fidelity (20251216) | openai | 1,390 | 536,869 |
| 8 | grok-imagine-image-quality (20260519) | xai | 1,390 | 35,601 |
| 9 | gemini-3-pro-image-2k (nano-banana-pro) | google | 1,390 | 548,733 |
| 10 | gemini-3.1-flash-image (nano-banana-2) [web-search] | google | 1,388 | 150,230 |
| 11 | gemini-3-pro-image-preview (nano-banana-pro) | google | 1,385 | 518,487 |
| 12 | reve-2.1 | reve | 1,375 | 19,119 |
| 13 | gpt-image-1.5-high-fidelity | openai | 1,370 | 559,765 |
| 14 | reve-2.0 | reve | 1,358 | 17,504 |
| 15 | uni-1.1-max | luma-ai | 1,333 | 40,918 |
Arene texte vers video
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | gemini-omni-1.1-flash | google | 1,515 | 1,777 |
| 2 | gemini-omni-flash | google | 1,511 | 21,934 |
| 3 | wan3.0 | alibaba | 1,494 | 1,167 |
| 4 | flux-3-video | bfl | 1,494 | 1,290 |
| 5 | grok-imagine-video-1.5-agent | xai | 1,491 | 1,195 |
| 6 | dreamina-seedance-2.5-720p | bytedance | 1,482 | 4,066 |
| 7 | dreamina-seedance-2.0-720p | bytedance | 1,479 | 52,864 |
| 8 | minimax-h3 | minimax | 1,462 | 7,648 |
| 9 | muse-video | meta | 1,456 | 2,178 |
| 10 | happyhorse-1.0 | aorizon | 1,427 | 22,116 |
| 11 | sora-2-pro | openai | 1,367 | 50,415 |
| 12 | veo-3.1-audio | google | 1,364 | 13,703 |
| 13 | veo-3.1-audio-1080p | google | 1,363 | 24,979 |
| 14 | veo-3.1-fast-audio | google | 1,362 | 39,373 |
| 15 | veo-3.1-fast-audio-1080p | google | 1,358 | 25,770 |
Arene edition video
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | wan3.0 | alibaba | 1,414 | 463 |
| 2 | dreamina-seedance-2.5-720p | bytedance | 1,410 | 429 |
| 3 | minimax-h3 | minimax | 1,392 | 962 |
| 4 | gemini-omni-flash | google | 1,367 | 2,109 |
| 5 | dreamina-seedance-2.0-720p | bytedance | 1,365 | 3,852 |
| 6 | happyhorse-1.0 | aorizon | 1,307 | 3,116 |
| 7 | grok-imagine-video | xai | 1,258 | 13,724 |
| 8 | kling-o3-pro | kling | 1,255 | 7,540 |
| 9 | kling-o1-pro | kling | 1,197 | 10,542 |
| 10 | runway-gen4-aleph | runway | 1,182 | 9,818 |
Arene recherche
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | gpt-5.6-sol-xhigh | openai | 1,257 | 29,663 |
| 2 | claude-opus-4-6-search | anthropic | 1,253 | 134,699 |
| 3 | gpt-5.5-search | openai | 1,242 | 89,873 |
| 4 | claude-opus-4-7 | anthropic | 1,233 | 91,394 |
| 5 | claude-fable-5 | anthropic | 1,230 | 41,795 |
| 6 | ernie-5.1 | baidu | 1,227 | 3,788 |
| 7 | claude-sonnet-4-6-search | anthropic | 1,221 | 134,905 |
| 8 | grok-4.5 | xai | 1,213 | 31,505 |
| 9 | gemini-3.1-pro-grounding | google | 1,210 | 113,282 |
| 10 | gemini-3-pro-grounding | google | 1,207 | 37,024 |
| 11 | gpt-5.2-search | openai | 1,207 | 52,712 |
| 12 | claude-opus-4-8 | anthropic | 1,204 | 70,998 |
| 13 | grok-4.20-multi-agent-beta-0309 | xai | 1,204 | 109,553 |
| 14 | gpt-5.1-search | openai | 1,199 | 59,909 |
| 15 | gemini-3-flash-grounding | google | 1,198 | 149,334 |
Arene agents
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | Claude Fable 5.1 (Max) | anthropic | | |
| 2 | Claude Opus 5 (High) | anthropic | | |
| 3 | Claude Opus 5 (Max) | anthropic | | |
| 4 | Claude Fable 5 (High) | anthropic | | |
| 5 | GPT 5.6 Sol (xHigh) | openai | | |
| 6 | Claude Opus 4.8 (High) | anthropic | | |
| 7 | Kimi K3 (Max) | moonshot | | |
| 8 | Claude Sonnet 5 (High) | anthropic | | |
| 9 | GPT 5.5 (xHigh) | openai | | |
| 10 | Hy4 preview | tencent | | |
| 11 | Claude Opus 4.7 (High) | anthropic | | |
| 12 | GLM 5.2 (Max) | zai | | |
| 13 | Grok 4.5 | xai | | |
| 14 | Claude Opus 4.7 | anthropic | | |
| 15 | GPT 5.5 (High) | openai | | |
Arene documents
| Rang | Modele | Organisation | Score Elo | Votes |
|---|
| 1 | claude-opus-5-high | anthropic | 1,520 | 1,663 |
| 2 | claude-opus-4-6 | anthropic | 1,510 | 37,271 |
| 3 | claude-opus-4-6-thinking | anthropic | 1,506 | 24,973 |
| 4 | claude-fable-5 | anthropic | 1,504 | 5,792 |
| 5 | claude-opus-4-7 | anthropic | 1,498 | 18,990 |
| 6 | claude-opus-4-7-thinking | anthropic | 1,497 | 18,793 |
| 7 | gpt-5.5-high | openai | 1,485 | 16,816 |
| 8 | claude-sonnet-4-6 | anthropic | 1,483 | 54,427 |
| 9 | gpt-5.5 | openai | 1,480 | 17,286 |
| 10 | gpt-5.6-terra-xhigh | openai | 1,479 | 1,969 |
| 11 | gpt-5.6-sol-xhigh | openai | 1,479 | 1,152 |
| 12 | claude-opus-4-8-thinking | anthropic | 1,475 | 8,388 |
| 13 | muse-spark-1.1 | meta | 1,472 | 2,054 |
| 14 | claude-sonnet-5-high | anthropic | 1,470 | 3,601 |
| 15 | gpt-5.4 | openai | 1,470 | 29,809 |
Autres classements
Artificial Analysis (Intelligence Index)
Metrique: AA Intelligence Index (0-100) · artificialanalysis.ai
| Rang | Modele | Organisation | Score | Votes |
|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) | Anthropic | 56.8 | |
| 2 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic | 56.2 | |
| 3 | GPT-6 Astra (max) | OpenAI | 54.7 | |
| 4 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic | 54.5 | |
| 5 | GPT-6 Astra (xhigh) | OpenAI | 54.3 | |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 54.1 | |
| 7 | GPT-6 Astra (high) | OpenAI | 53.4 | |
| 8 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 53.4 | |
| 9 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 53.2 | |
| 10 | Muse Spark 1.3 (max) | Meta | 53 | |
| 11 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback) | Anthropic | 52.8 | |
| 12 | GPT-6 Astra (medium) | OpenAI | 52.2 | |
| 13 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 52 | |
| 14 | Muse Spark 1.3 (xhigh) | Meta | 51.6 | |
| 15 | GPT-5.6 Sol (max) | OpenAI | 51.3 | |
BenchLM
Metrique: aggregated display score · benchlm.ai
| Rang | Modele | Organisation | Score | Votes |
|---|
| 1 | Claude Fable 5.1 | Anthropic | 83 | |
| 2 | GPT-6 Astra | OpenAI | 81.1 | |
| 3 | Claude Fable 5 | Anthropic | 80.9 | |
| 4 | Claude Opus 5 | Anthropic | 80.7 | |
| 5 | GPT-5.6 Sol | OpenAI | 79.6 | |
| 6 | Gemini 3.8 Flash | Google | 78.4 | |
| 7 | Kimi K3 | Moonshot AI | 74.9 | |
| 8 | GPT-5.5 | OpenAI | 73.3 | |
| 9 | Qwen3.8 Max | Alibaba | 72.4 | |
| 10 | Claude Opus 4.8 | Anthropic | 72.3 | |
| 11 | Muse Spark 1.2 | Meta | 71.9 | |
| 12 | Muse Spark 1.1 | Meta | 71.8 | |
| 13 | GPT-5.6 Terra | OpenAI | 71.4 | |
| 14 | GPT-5.4 | OpenAI | 71 | |
| 15 | Claude Sonnet 5 | Anthropic | 70.8 | |
Aider polyglot (coding)
Metrique: pass rate 2 (%) · aider.chat/docs/leaderboards/
| Rang | Modele | Organisation | Score | Votes |
|---|
| 1 | gpt-5 (high) | | 88 | |
| 2 | gpt-5 (medium) | | 86.7 | |
| 3 | o3-pro (high) | | 84.9 | |
| 4 | gemini-2.5-pro-preview-06-05 (32k think) | | 83.1 | |
| 5 | o3 (high) | | 81.3 | |
| 6 | gpt-5 (low) | | 81.3 | |
| 7 | grok-4 (high) | | 79.6 | |
| 8 | gemini-2.5-pro-preview-06-05 (default think) | | 79.1 | |
| 9 | o3 (high) + gpt-4.1 | | 78.2 | |
| 10 | Gemini 2.5 Pro Preview 05-06 | | 76.9 | |
| 11 | o3 | | 76.9 | |
| 12 | DeepSeek-V3.2-Exp (Reasoner) | | 74.2 | |
| 13 | Gemini 2.5 Pro Preview 03-25 | | 72.9 | |
| 14 | o4-mini (high) | | 72 | |
| 15 | claude-opus-4-20250514 (32k thinking) | | 72 | |
LiveBench
Metrique: average score (0-100) · livebench.ai
| Rang | Modele | Organisation | Score | Votes |
|---|
| 1 | claude-fable-5-1-max-effort | | 83.8 | |
| 2 | claude-fable-5-max-effort | | 83.4 | |
| 3 | gpt-6-astra-max | | 83.1 | |
| 4 | muse-spark-1.3-xhigh | | 82.4 | |
| 5 | gpt-5.6-sol-max | | 81.7 | |
| 6 | gpt-5.5-xhigh | | 80.8 | |
| 7 | claude-opus-5-max-effort | | 80.5 | |
| 8 | gemini-3.7-flash-high | | 79.9 | |
| 9 | smaug-agentic | | 79.7 | |
| 10 | qwen3.8-max | | 79.5 | |
| 11 | kimi-k3 | | 79.5 | |
| 12 | grok-4.6 | | 79 | |
| 13 | muse-spark-1.2-xhigh | | 78.9 | |
| 14 | gpt-5.4-xhigh | | 78.8 | |
| 15 | gpt-5.6-terra-max | | 78.6 | |
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.