Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015
Pro Mode — raw scores, one benchmark under the lensofficial card harness
The field · 19 measured
34.9686.2

19 models measured, most on the official card harness. MiMo V2 Flash tops the board at 86.2.

19 measured·Lifecycle Updated Oct 8, 2026Score basis
#◆Vendor$/M in$/M out
Leader — ignites whiteField — fill cools with scoreBars show 34.96–86.2 · ◆ solid = first-party or better · outlined = arm's-length
01MiMo V2 FlashXiaomi86.2$0.10/M$0.30/M$0.002
02Qwen3 Next 80B A3B InstructAlibaba82.7$0.15/M$1.2/M$0.008
03Qwen3 235B A22B Instruct 2507Alibaba79.2$0.23/M$0.92/M$0.007
04Qwen3 VL 235B A22B InstructAlibaba77.4$0.40/M$1.6/M$0.013
05Nemotron 3 Super 120B A12B+1 altNVIDIA73.88$0.30/M$0.90/M$0.008
06Sarvam 105BSarvam AI71$0.04/M$0.17/M$0.001
07NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16NVIDIA68.63P———
08Granite 4.2 30B+1 altIBM67.93$0.16/M$0.65/M$0.006
09NVIDIA Nemotron 3 Nano 30B A3BNVIDIA67.7$0.05/M$0.20/M$0.002
10Granite 4.2 8B+2 altsIBM65.19$0.06/M$0.25/M$0.002
11Qwen3 VL 32B InstructAlibaba64.7$0.16/M$0.64/M$0.006
12Qwen3 Next 80B A3BAlibaba62.3$0.15/M$1.2/M$0.011
13Qwen3 VL 32B ReasoningAlibaba60.5$0.16/M$0.64/M$0.007
14Qwen3 VL 30B A3B InstructAlibaba58.5$0.20/M$0.80/M$0.009
15Qwen3 VL 30B A3B ReasoningAlibaba56.7$0.20/M$2.4/M$0.023
16Qwen3 VL Thinking (8B)Alibaba51.1$0.18/M$2.1/M$0.022
17Sarvam 30BSarvam AI49$0.03/M$0.11/M$0.001
18Qwen3 VL 4B (Reasoning)Alibaba36.8———
19Granite 4.2 3B+2 altsIBM34.96$0.03/M$0.12/M$0.002
◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 19 models scored · 0 independently verified · 19 vendor-reported · 0 with source disagreement. How these tiers are assigned