Compare/Gemma 4 31B (Reasoning) vs gpt-oss-120b (low)

Gemma 4 31B (Reasoning)vsgpt-oss-120b (low)

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

Google

Gemma 4 31B (Reasoning)

Input
$0/M
Output
$0/M
Speed
36 tok/s
TTFT
1.11s
OpenAI

gpt-oss-120b (low)

Input
$0.15/M
Output
$0.59/M
Speed
160 tok/s
TTFT
0.89s

Winner by Category

Cheaper
Gemma 4 31B (Reasoning)
Faster (tok/s)
gpt-oss-120b (low)
Lower Latency
gpt-oss-120b (low)
Benchmarks (2-0)
Gemma 4 31B (Reasoning)

Pricing Comparison

MetricGemma 4 31B (Reasoning)gpt-oss-120b (low)
Input ($/M tokens)$0$0.15
Output ($/M tokens)$0$0.59
Cost for 1M input + 100K output tokens:
Gemma 4 31B (Reasoning)$0.00
gpt-oss-120b (low)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Gemma 4 31B (Reasoning)
36 tok/s
gpt-oss-120b (low)
160 tok/s
Time to First Token (seconds) — lower is better
Gemma 4 31B (Reasoning)
1.11s
gpt-oss-120b (low)
0.89s

Editorial Analysis

Verdict. Gemma 4 31B (Reasoning) wins the overall benchmark matchup 2–0 across 2 overlapping categories, but raw benchmark score is only one input to the decision.

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. Gemma 4 31B (Reasoning) is strongest on Coding Index (43.4), Intelligence Index (29.7). gpt-oss-120b (low) leads on Coding Index (21.2), Intelligence Index (14.9).

Speed. On throughput, gpt-oss-120b (low) generates tokens at 160 tok/s versus 36 tok/s — about 78% faster. On time-to-first-token, gpt-oss-120b (low) responds in 890ms vs 1110ms, which matters most for chat-style UIs.

Provider. Google and OpenAI sell to overlapping but distinct developer audiences: Google tends to ship frontier reasoning models with premium positioning, while OpenAI 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): Gemma 4 31B (Reasoning) costs $0.00 ($0/year); gpt-oss-120b (low) costs $13.35 ($160/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Gemma 4 31B (Reasoning) ≈ $0.00/run, gpt-oss-120b (low) ≈ $1.93/run. At agent/realtime scale (200M input / 100M output per million requests): Gemma 4 31B (Reasoning) ≈ $0/run, gpt-oss-120b (low) ≈ $89/run. Gemma 4 31B (Reasoning) 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.

Head-to-head deltas

  • On throughput, gpt-oss-120b (low) is 4.46× faster (160 tok/s vs 36 tok/s). For streaming chat or real-time agents this alone often flips the recommendation.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
29.714.9
Coding Index
43.421.2
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
Gemma 4 31B (Reasoning)2 wins
0 winsgpt-oss-120b (low)

Frequently Asked Questions

Which is cheaper, Gemma 4 31B (Reasoning) or gpt-oss-120b (low)?

Gemma 4 31B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.26/M for gpt-oss-120b (low).

Which model performs better on benchmarks?

Gemma 4 31B (Reasoning) wins 2 out of 12 benchmarks compared to 0 for gpt-oss-120b (low). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-120b (low) generates tokens faster at 160 tok/s vs 36 tok/s. However, gpt-oss-120b (low) has lower time-to-first-token (0.89s vs 1.11s).

When should I use Gemma 4 31B (Reasoning) vs gpt-oss-120b (low)?

Choose based on your priorities: Gemma 4 31B (Reasoning) for lower cost, Gemma 4 31B (Reasoning) for stronger benchmark performance, and gpt-oss-120b (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.