Beam 1.0 501B A23B vs Ling 3.1 Flash, head to head

Side A

Side B

Overall

Beam 1.0 501B A23B is clearly better. It wins 36 of the 54 test cases where they differ.

Learn to build evals like this in the AI Engineering Academy

Task by task

A score turns orange only when that model wins clearly more of the task's test cases. Under each score, the average time per test case on the machine it ran on. Ling 3.1 Flash spends 1.6× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskABeam 1.0 501B A23BBLing 3.1 FlashBeam 1.0 501B A23BLing 3.1 Flash

Overall

5717.2s

4K7.9K

451m 16s

Agents

Runs multi-step jobs through tools, within a written policy

5521.8s

4.8K4.5K

4155.9s

Structured Extraction

Turns logs, diffs and records into exact JSON

819.98s

3.4K8.1K

711m 11s

Coding

Writes code and SQL that pass hidden tests

4819.9s

4.5K11.3K

241m 42s

Grounded Answers

Answers from the given documents with sources, never guesses

6911.6s

2.7K6.7K

5258.9s

Instruction Following

Applies every rule, including ones changed mid-conversation

7820.9s

5.6K11.4K

761m 55s

Business Logic

Computes billing, scheduling and pricing rules exactly

5714.0s

4.2K9.7K

381m 22s

Security & permissions

Ignores planted instructions, still does the allowed work

5120.6s

3.2K5.2K

5456.1s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

1724.3s

3.1K3.2K

042.1s

What you'd run

The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.

SpecABeam 1.0 501B A23BBLing 3.1 Flash

Speed

274 tok/s

112 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

Cost per run

$0.83

Not measured

Cost per case

$0.0054

Not measured

Time per case

17.2s

1m 16s

Quantization

FP8

—

Harness

openrouter

The race

2 lead changes

Each model's running score as the test cases go by. The dashed line is a perfect run.

Beam 1.0 501B A23BLing 3.1 Flash

Every test case

153 test cases

Each square is one test case, colored by the model that scored higher.

Agents83

Structured Extraction53

Coding72

Grounded Answers51

Instruction Following13

Business Logic51

Security & permissions45

Diagnosis & investigation10

36 won by Beam 1.0 501B A23B18 won by Ling 3.1 Flash99 tied