Atlas

Compare Models

Grok 4.7 vs Qwen3.8-Max

Grok 4.7 leads by 0.9 capability points (≈95% interval −1.4 to +3.3): statistically tied · P(higher) ≈ 78%

Wins 19 of 27 shared benchmarks (8 lost)

Capability vs. relative cost
Grok 4.7Qwen3.8-MaxClosed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

Grok 4.7vsQwen3.8-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins19 – 8 · 27 shared

Comparing matching setups only (261 benchmarks excluded) · suites counted once
← Grok 4.7Qwen3.8-Max →

Grok 4.7vsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Vercel and 7 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Qwen3.8-Max minus Grok 4.7.

GameBench 2Games72.351.4−20.9
AutomationBench-AA 1.0.6Agents65.649.2−16.3
AA-Briefcase v1.1 EloAgents16571382−15.1
YC-BenchGames16663892095838+15.0
AA-Omniscience IndexIndexes32.03.4−14.3
BuseyBench SVGMultimodal4.65.4+8.5
DeepsecBench — Revalidated V1Code7.815.5+7.7
DeepsecBench — Revalidated V1 (233 issues)Code7.815.5+7.7
Terminal-Bench 4.0 (Artificial Analysis)Code25.818.7−7.1
Artificial Analysis Intelligence Index v4.3.2Indexes46.440.2−6.3
RSI-Exam 0.1 (Full 88)Agents0.40.3−6.2
Conceptual Reasoning IndexIndexes63.159.4−5.1
GDPval-AA v2.1Professional Work17181611−4.7
SciCode 1.0.1 (Artificial Analysis)Code57.853.2−4.5
Medical Long Context Reasoning (MLCR-AA)Health & Medicine15.019.4+4.4
MMMU ProMultimodal78.282.3+4.2
DTBenchGeneral QA96.092.0−4.0
Terminal-Bench 2.1Code85.081.3−3.7
LMCAGeneral QA49.446.2−3.1
GDP.pdf (Artificial Analysis, All-pass)Professional Work23.220.2−3.0
Ramp Accounting BenchFinance & Accounting44.141.2−2.9
ACCoRDGeneral QA74.071.4−2.6
CritPt (avg@5)Science18.020.0+2.0
AA-LCR v1.1Search80.078.3−1.7
Epoch Capabilities Index (ECI)Indexes156157+1.1
Artificial Analysis Progress Index v1Indexes323320−1.1
Humanity's Last Exam (Text-Only)General QA43.143.0−0.1

Grok 4.7vsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, Vercel and 7 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…