Atlas

Compare Models

Claude Haiku 5.5 vs Qwen3.8-Max

Claude Haiku 5.5 leads by 1.7 capability points (≈95% interval −0.7 to +4.0): statistically tied · P(higher) ≈ 91%

Wins 19 of 25 shared benchmarks (5 lost, 1 tied)

Capability vs. relative cost
Claude Haiku 5.5Qwen3.8-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.

Claude Haiku 5.5vsQwen3.8-Maxcapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins19 – 5 · 25 shared, 1 tied

Comparing matching setups only (224 benchmarks excluded) · suites counted once
← Claude Haiku 5.5Qwen3.8-Max →

Claude Haiku 5.5vsQwen3.8-Maxwins by categoryData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, BuseyBench 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 Claude Haiku 5.5.

Medical Long Context Reasoning (MLCR-AA)Health & Medicine63.319.4−43.9
Cresta-BenchAgents20.148.7+28.6
GameBench 2Games75.151.4−23.6
Terminal-Bench 4.0 (Artificial Analysis)Code32.818.7−14.1
AutomationBench-AA 1.0.6Agents36.049.2+13.3
AA-Briefcase v1.1 EloAgents15731382−10.5
ACCoRDGeneral QA81.571.4−10.1
BuseyBench SVGMultimodal4.65.4+8.6
Conceptual Reasoning IndexIndexes65.359.4−8.1
LMCAGeneral QA51.146.2−4.8
Terminal-Bench 2.1Code85.081.3−3.7
AA-Omniscience IndexIndexes10.73.4−3.6
Artificial Analysis Intelligence Index v4.3.2Indexes43.440.2−3.2
MMMU ProMultimodal79.182.3+3.2
DTBenchGeneral QA95.092.0−3.0
CritPt (avg@5)Science22.620.0−2.6
Artificial Analysis Progress Index v1Indexes326320−2.3
Epoch Capabilities Index (ECI)Indexes160157−2.3
SciCode 1.0.1 (Artificial Analysis)Code55.053.2−1.7
Humanity's Last Exam (with tools)General QA57.456.2−1.2
Ramp Accounting BenchFinance & Accounting42.341.2−1.1
GDPval-AA v2.1Professional Work16291611−0.8
GDP.pdf (Artificial Analysis, All-pass)Professional Work20.820.2−0.6
Humanity's Last Exam (Text-Only)General QA42.743.0+0.4
AA-LCR v1.1Search78.378.30.0

Claude Haiku 5.5vsQwen3.8-Maxnormalised score marginsData Nov 15, 2026Data: Artificial Analysis, Conceptual Reasoning Benchmark Authors, BuseyBench 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…