Robot Intelligence Index
A unified ranking of robot policies built from 23 sim and real-world benchmarks.
Overall
Best-ranked model from each lab
Rating vs speed
Median time per task attempt in this view · hollow dots are estimates
Rating vs cost
Median compute cost per task attempt · hollow dots are estimates
ModelRank rangeModel weights
1
Claude Fable 5.2Anthropic · LLM1989± 41–2$7.60est.3 min 18 sest.4ClosedNov 09, 20262
SLA-PreviewHKUST(GZ) & OLA · VLA1807± 101–8$0.041est.45 sest.2OpenNov 05, 20263
Dream-1Dream Labs · WAM1756± 512–22$0.116est.2 min 20 sest.2ClosedOct 19, 20264
GPT-6 AstraOpenAI · LLM1733± 252–10$17.74est.3 min 01 sest.10ClosedSep 03, 20265
GPT-6.1 SolOpenAI · LLM1726± 122–11$2.15est.4 min 02 sest.5ClosedSep 29, 20266
InternW0-ΔShanghai AI Lab · WAM1723± 113–10$0.028est.30 sest.3OpenSep 25, 20267
MWA-PhoenixAnyverse & OpenPhoenix · WAM1690± 103–9$0.041est.45 sest.2OpenOct 21, 20268
Gemini 4 ArgonGoogle · LLM1685± 143–12$3.08est.25 min 54 sest.6ClosedSep 30, 20269
Cosmos3-Nano-PolicyNVIDIA · WAM1668± 94–12$0.045est.49 sest.3OpenMay 31, 202610
OpenWAM-αOpenWAM team · WAM1666± 174–13$0.030est.33 sest.4OpenSep 07, 202611
Claude Opus 5.5Anthropic · LLM1630± 215–13$6.17est.3 min 06 sest.7ClosedSep 22, 202612
FLUX 3 ActionBlack Forest Labs · WAM1618± 354–16$0.052est.57 sest.2OpenSep 23, 202613
DreamZeroNVIDIA · WAM1596± 302–17$0.048est.52 sest.3OpenFeb 17, 202614
π0.5Physical Intelligence · VLA1517± 2210–16$0.030est.33 sest.18OpenApr 22, 202515
Gemini 3.8 FlashGoogle · LLM1489± 212–20$3.9643 min 21 s2ClosedSep 02, 202616
MolmoAct2Ai2 · VLA1411± 2612–25$0.038est.41 sest.10OpenMay 05, 202617
InternVLA-A1Shanghai AI Lab · VLA1405± 3213–28$0.045est.49 sest.2OpenJan 05, 202618
GalaxeaVLA G0.5Galaxea AI · VLA1396± 2712–26$0.036est.40 sest.5OpenJun 16, 202619
Muse Wonder 1.0Meta · LLM1369± 3113–28$1.52est.4 min 33 sest.2ClosedOct 12, 202620
LingBot-VLA v2Robbyant (Ant Group) · VLA1368± 614–26$0.036est.40 sest.3OpenJul 07, 202621
GalaxeaVLA G0Galaxea AI · VLA1367± 1315–27$0.028est.30 sest.3OpenAug 30, 202522
π0-FASTPhysical Intelligence · VLA1352± 1914–26$0.014est.16 sest.6OpenJan 16, 202523
GR00T N1.6NVIDIA · VLA1350± 2613–28$0.077est.84 sest.3OpenSep 29, 202524
Xiaomi-Robotics-0Xiaomi · VLA1347± 1617–27$0.031est.34 sest.4OpenFeb 12, 202625
DeepSeek V4.1 FlashDeepSeek · LLM1346± 1715–28$0.277est.7 min 05 sest.3OpenSep 10, 202626
GR00T N1.7NVIDIA · VLA1332± 2916–28$0.035est.38 sest.12OpenMar 16, 202627
GLM 5.3 FlashZhipu · LLM1332± 1813–29$0.31552 min 22 s2OpenAug 26, 202628
X-VLATsinghua AIR et al. · VLA1288± 3716–32$0.027est.30 sest.8OpenOct 11, 202529
π0Physical Intelligence · VLA1243± 2323–33$0.029est.31 sest.15OpenOct 31, 202430
StarVLAStarVLA team · VLA1231± 1416–33$0.030est.33 sest.3OpenOct 15, 202531
Diffusion PolicyColumbia / TRI · Baseline1210± 2420–35$0.028est.31 sest.4OpenMar 07, 202332
DM0Dexmal · VLA1206± 3011–35$0.061est.67 sest.3OpenFeb 10, 202633
Spirit v1.5Spirit AI · VLA1117± 427–35$0.045est.49 sest.2OpenJan 12, 202634
ACTStanford · Baseline1108± 1327–35$0.030est.33 sest.5OpenApr 23, 202335
SmolVLAHugging Face · VLA1102± 1425–36$0.027est.30 sest.5OpenJun 02, 202536
PaliGemma-binningPhysical Intelligence · VLA1060± 028–36$0.051est.55 sest.2OpenJun 22, 2025Ranked as in the Robot Intelligence Index: rank and its plausible range within the chosen coverage. The ± under a rating is its spread, how much the model’s finishes differ across benchmarks, not uncertainty in the rating. Cost and time are per task attempt, median across the view’s benchmarks; est. marks Playground estimates. Methodology