Beam 1.0 · Intelligence Index v5.0 ↗
1 more reported result
30.33 index · Beam 1.0 · Intelligence Index v4.3.2 · Artificial Analysis ↗
Reflection / MODEL EVIDENCE
Beam 1.0
35 benchmarks · 41 observations · 35 sources · released 2026-10-16
Scores at a glance
35 benchmarks · large dot: Beam 1.0; small dots: closest models where reported
AA-Briefcase v1.1 ↗976.20 Elo
Beam 1.0 · AA-Briefcase v1.1 · overall Elo ↗
AutomationBench-AA ↗48.46%
Beam 1.0 · AutomationBench-AA · guardrail-gated objective score ↗
GDP.pdf ↗11.60%
Beam 1.0 · GDP.pdf · all-pass ↗
Terminal-Bench 4.0 ↗3.03%
Beam 1.0 · Terminal-Bench 4.0 · AA harness ↗
1 more reported result
4.04 % · Beam 1.0 (Mini-SWE-agent) · Terminal-Bench 4.0 · Score · Vals AI · Terminal-Bench 4.0 ↗
Beam 1.0 · Terminal-Bench-Science 0.1 · AA harness ↗
1 more reported result
1.43 % · Beam 1.0 (Mini-SWE-agent) · Terminal-Bench-Science · Score · Vals AI · Terminal-Bench-Science ↗
FrontierCode 2.0 ↗5.53%
Beam 1.0 · FrontierCode 2.0 · AA implementation ↗
Beam 1.0 · CritPt v2 · hard subset · AA implementation ↗
HLE-Diamond ↗12.80%
Beam 1.0 · HLE-Diamond · AA implementation ↗
AA-Omniscience v1.1 ↗2.33 index
Beam 1.0 · AA-Omniscience v1.1 · error-penalized index ↗
1 more reported result
1.50 index · Beam 1.0 · AA-Omniscience · error-penalized score · Artificial Analysis ↗
Beam 1.0 · AA-Omniscience v1.1 · accuracy ↗
1 more reported result
33.07% · Beam 1.0 · AA-Omniscience · accuracy · Artificial Analysis ↗
Beam 1.0 · AA-Omniscience v1.1 · hallucination rate, lower is better ↗
1 more reported result
47.16% · Beam 1.0 · AA-Omniscience · hallucination rate, lower is better · Artificial Analysis ↗
GDPval-AA v2.1 ↗1177.08 Elo
Beam 1.0 · GDPval-AA v2.1 · Elo ↗
FrontierCode 1.1 ↗24.32%
Beam 1.0 · FrontierCode 1.1 · AA implementation ↗
AA-LCR v1.1 ↗78.00%
Beam 1.0 · AA-LCR v1.1 ↗
SciCode ↗48.50%
Beam 1.0 · SciCode · AA implementation ↗
Humanity’s Last Exam ↗34.66%
Beam 1.0 · Humanity’s Last Exam · AA implementation ↗
MLCR-AA ↗17.78%
Beam 1.0 · MLCR-AA · overall ↗
CritPt v2 ↗40.00%
Beam 1.0 · CritPt v2 · code tools ↗
CritPt ↗13.14%
Beam 1.0 · CritPt · original ↗
Vals Index ↗43.42 %
Beam 1.0 · Vals Index · Accuracy ↗
Vals Finance Index ↗46.5 %
Beam 1.0 · Vals Finance Index · Accuracy ↗
Vals Legal Index ↗61.8 %
Beam 1.0 · Vals Legal Index · Accuracy ↗
Vals Science Index ↗22.03 %
Beam 1.0 · Vals Science Index · Accuracy ↗
Legal Research Bench ↗28.85 %
Beam 1.0 · Legal Research Bench · All-Pass ↗
HLAB-Vals-1.1 ↗4.58 %
Beam 1.0 · HLAB-Vals-1.1 · Task Pass Rate ↗
Vals Finance Agent v2.1 ↗51.83 %
Beam 1.0 · Finance Agent · Accuracy ↗
Beam 1.0 · Excel Modeling Benchmark · Accuracy ↗
Tax Agent Bench ↗8.81 %
Beam 1.0 · Tax Agent Bench · Accuracy ↗
ProofBench ↗18 %
Beam 1.0 · ProofBench · Accuracy ↗
BioMysteryBench ↗42.59 %
Beam 1.0 · BioMysteryBench · Accuracy ↗
MysteryMechanism ↗22.07 %
Beam 1.0 · MysteryMechanism · Accuracy ↗
Vibe Code Bench ↗66.44 %
Beam 1.0 (OpenHands) · Vibe Code Bench · original task set ↗
Code Migration v1.1 ↗22.85 %
Beam 1.0 · Code Migration · Accuracy ↗
IOI v1 & IOI v2 ↗22.83 %
Beam 1.0 · IOI · Accuracy ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
30 of 34 shared benchmark comparisons
27 of 34 shared benchmark comparisons
GPT-6 Luna →OpenAI
33 of 34 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗
- Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗
- AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗
- AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗
- CritPt Benchmark | Artificial Analysis ↗
- CritPt v2 Benchmark | Artificial Analysis ↗
- CritPt v2 — Hard Subset — Artificial Analysis ↗
- FrontierCode 1.1 Benchmark | Artificial Analysis ↗
- FrontierCode 2.0 Benchmark — Artificial Analysis ↗
- GDP.pdf Benchmark | Artificial Analysis ↗
- GDPval-AA v2.1 Benchmark | Artificial Analysis ↗
- HLE-Diamond Benchmark — Artificial Analysis ↗
- Humanity's Last Exam Benchmark | Artificial Analysis ↗
- MLCR-AA: Medical Long Context Reasoning Benchmark | Artificial Analysis ↗
- AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗
- Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗
- BioMysteryBench — evaluation methodology and results ↗
- Code Migration — evaluation methodology and results ↗
- Excel Modeling Benchmark — evaluation methodology and results ↗
- Finance Agent — evaluation methodology and results ↗
- Vals Finance Index — evaluation methodology and results ↗
- HLAB-Vals-1.1 — evaluation methodology and results ↗
- IOI — evaluation methodology and results ↗
- Vals Legal Index — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MysteryMechanism — evaluation methodology and results ↗
- ProofBench — evaluation methodology and results ↗
- Vals Science Index — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- Terminal-Bench 4.0 — evaluation methodology and results ↗
- Terminal-Bench-Science — evaluation methodology and results ↗
- Vals Index — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Beam 1.0 · Beam 1.0 (Mini-SWE-agent) · Beam 1.0 (OpenHands)