Arena Elo movers — who's climbing and who's slipping
| Model | Elo | Prior | Δ | |
|---|---|---|---|---|
| #91 | glm-5v-turbo Z.ai | 1433.2 | 1227.2 | +206.0 |
| #58 | gpt-5-medium OpenAI | 1419.0 | 1394.0 | +25.0 |
| #115 | grok-code-fast-1 SpaceXAI | 1164.3 | 1139.7 | +24.6 |
| #3 | dreamina-seedance-2.0-720p Bytedance | 1481.7 | 1457.3 | +24.5 |
| #38 | ltx-2-19b | 1151.1 | 1134.9 | +16.2 |
| #96 | mimo-v2-omni Xiaomi | 1430.0 | 1414.4 | +15.6 |
| #45 | gpt-5.5 (codex-harness) OpenAI | 1457.2 | 1444.3 | +12.8 |
| #35 | seedream-5.0-lite Bytedance | 1136.6 | 1126.5 | +10.0 |
| #7 | kling-o3-pro KlingAI | 1256.5 | 1246.7 | +9.8 |
| #37 | gpt-5.5-high (codex-harness) OpenAI | 1486.1 | 1478.9 | +7.2 |
| #91 | gpt-5.1-codex OpenAI | 1336.3 | 1329.4 | +7.0 |
| #22 | claude-sonnet-4-5-search Anthropic | 1158.5 | 1151.6 | +6.9 |
| #43 | gpt-5.4-high (codex-harness) OpenAI | 1462.9 | 1457.2 | +5.7 |
| #30 | hailuo-2.3 MiniMax | 1204.3 | 1198.6 | +5.7 |
| #19 | uni-1.1 Luma AI | 1181.2 | 1176.0 | +5.2 |
| #49 | gpt-5.4-medium (codex-harness) OpenAI | 1442.1 | 1437.3 | +4.8 |
| #45 | recraft-v4 Recraft | 1113.8 | 1109.9 | +3.9 |
| #105 | gpt-5.1-codex-mini OpenAI | 1243.6 | 1239.7 | +3.9 |
| #53 | deepseek-v4-pro DeepSeek | 1457.8 | 1454.2 | +3.6 |
| #32 | seedream-4.5 Bytedance | 1146.6 | 1143.0 | +3.6 |
| Model | Elo | Prior | Δ | |
|---|---|---|---|---|
| #115 | molmo-2-8b Ai2 | 1107.9 | 1327.9 | -220.0 |
| #113 | gpt-4o-2024-08-06 OpenAI | 1119.4 | 1334.8 | -215.4 |
| #114 | gpt-4-turbo-2024-04-09 OpenAI | 1112.4 | 1323.8 | -211.4 |
| #101 | claude-3-5-sonnet-20240620 Anthropic | 1145.5 | 1342.1 | -196.6 |
| #99 | gpt-5-nano-high OpenAI | 1147.6 | 1337.3 | -189.6 |
| #90 | gpt-4o-2024-05-13 OpenAI | 1162.4 | 1345.5 | -183.2 |
| #114 | mercury-2 Inception AI | 1166.2 | 1346.6 | -180.4 |
| #100 | llama-4-maverick-17b-128e-instruct Meta | 1146.8 | 1327.0 | -180.2 |
| #97 | minimax-m2 MiniMax | 1296.9 | 1346.3 | -49.4 |
| #28 | qwen3.7-max-20260517 Alibaba | 1516.7 | 1540.8 | -24.1 |
| #9 | runway-gen4-aleph Runway | 1182.9 | 1204.4 | -21.4 |
| #24 | runway-gen-4.5 Runway | 1222.7 | 1235.0 | -12.3 |
| #18 | wan2.6-t2v Alibaba | 1329.8 | 1341.5 | -11.6 |
| #14 | grok-imagine-video-720p SpaceXAI | 1345.4 | 1357.0 | -11.6 |
| #117 | devstral-medium-2507 Mistral | 1079.9 | 1091.3 | -11.5 |
| #21 | wan2.5-t2v-preview Alibaba | 1248.8 | 1259.8 | -10.9 |
| #113 | granite-4.1-8b IBM | 1192.5 | 1202.0 | -9.5 |
| #10 | veo-3.1-audio-1080p Google | 1362.9 | 1371.6 | -8.7 |
| #13 | gemini-3-flash-grounding Google | 1197.3 | 1205.8 | -8.6 |
| #7 | happyhorse-1.0 Alibaba-ATH | 1428.0 | 1434.8 | -6.8 |
claude-fable-5claude-opus-4-5-20251101-high-32kclaude-opus-4-6-highclaude-opus-4-7-highclaude-opus-4-8claude-opus-4-8-highclaude-opus-5-highclaude-opus-5-maxclaude-sonnet-4-5-20250929-high-32kclaude-sonnet-5-highclaude-sonnet-5-searchCosmos3-Super-Text2ImageCosmos3-Super-Text2Image (Agentic)deepseek-v4-flash-highdeepseek-v4-flash-high-preview