Compare/Olmo 3.1 32B Think vs Mercury 2

Olmo 3.1 32B ThinkvsMercury 2

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Allen Institute for AI

Olmo 3.1 32B Think

Input
$0/M
Output
$0/M
Speed
TTFT
Inception

Mercury 2

Input
$0.25/M
Output
$0.75/M
Speed
835 tok/s
TTFT
3.93s

Winner by Category

Cheaper
Olmo 3.1 32B Think
Faster (tok/s)
Mercury 2
Lower Latency
Mercury 2
Benchmarks (0-2)
Mercury 2

Pricing Comparison

MetricOlmo 3.1 32B ThinkMercury 2
Input ($/M tokens)$0$0.25
Output ($/M tokens)$0$0.75
Cost for 1M input + 100K output tokens:
Olmo 3.1 32B Think$0.00
Mercury 2$0.33

Speed Comparison

Output Speed (tokens/s) — higher is better
Olmo 3.1 32B Think
Mercury 2
835 tok/s
Time to First Token (seconds) — lower is better
Olmo 3.1 32B Think
Mercury 2
3.93s

Editorial Analysis

Verdict. Mercury 2 takes the aggregate benchmark matchup 2–0 across 2 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.

Pricing. Pricing varies significantly between these models — check the table above for the exact per-token rates. Many production workloads actually surface input-token cost (retrieval-augmented prompts, code-context windows), so factor both directions.

Strengths. Olmo 3.1 32B Think is strongest on Intelligence Index (7.9). Mercury 2 leads on Coding Index (31.1), Intelligence Index (21.9).

Speed. Speed data is incomplete for this pair; benchmark and price should decide.

Provider. Allen Institute for AI and Inception sell to overlapping but distinct developer audiences: Allen Institute for AI tends to ship frontier reasoning models with premium positioning, while Inception often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.

Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Olmo 3.1 32B Think costs $0.00 ($0/year); Mercury 2 costs $18.75 ($225/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Olmo 3.1 32B Think ≈ $0.00/run, Mercury 2 ≈ $2.75/run. At agent/realtime scale (200M input / 100M output per million requests): Olmo 3.1 32B Think ≈ $0/run, Mercury 2 ≈ $125/run. Olmo 3.1 32B Think becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.

Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
7.921.9
Coding Index
31.1
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
Olmo 3.1 32B Think0 wins
2 winsMercury 2

Frequently Asked Questions

Which is cheaper, Olmo 3.1 32B Think or Mercury 2?

Olmo 3.1 32B Think is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.38/M for Mercury 2.

Which model performs better on benchmarks?

Mercury 2 wins 2 out of 12 benchmarks compared to 0 for Olmo 3.1 32B Think. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mercury 2 generates tokens faster at 835 tok/s vs — tok/s. However, Mercury 2 has lower time-to-first-token (3.93s vs —s).

When should I use Olmo 3.1 32B Think vs Mercury 2?

Choose based on your priorities: Olmo 3.1 32B Think for lower cost, Mercury 2 for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.