LLM Rank.top

Leaderboard · Model · Updated

o3

OpenAI's reasoning model (chain-of-thought); strongest on math, science, agentic coding.

Composite 83.7 Rank #2 of 30 OpenAI frontier Closed / proprietary Released 2025-04
Try o3 → Compare with Grok 4 → Or route via OpenRouter →

At a glance

ProviderOpenAI
Released2025-04
Tierfrontier
LicenseClosed / proprietary
Modalitiestext, image
Context window200k tokens
Max output100k tokens
API price · input$2.00 / 1M tokens
API price · output$8.00 / 1M tokens

Benchmark performance

How o3 stacks up against the current leader (GPT-5) and the median model in the leaderboard:

Benchmarko3GPT-5Median
Chatbot Arena Elo 1380 1410 1320
MMLU-Pro 85.7 86.8 78.0
GPQA Diamond 87.7 87.3 65.0
MATH 96.7 96.7 78.3
HumanEval 92.7 95.1 92.0
SWE-Bench Verified 71.7 74.9 49.0

Numbers compiled from provider technical reports and Chatbot Arena. See methodology for the composite-score formula.

Don't lock in to one provider.

OpenRouter routes your requests across o3, GPT-5, Claude, Gemini, and 100+ other models behind a single API key — pay-as-you-go, no monthly minimum. Try OpenRouter → (affiliate · supports this site)

What does o3 cost in practice?

API pricing is $2.00 per 1M input tokens and $8.00 per 1M output tokens. Assuming a 50/50 input/output split, here is what that looks like at three workload sizes:

VolumePer dayPer monthPer year
1M tokens/day$5.00$150.00$1,825
10M tokens/day$50.00$1,500$18,250
100M tokens/day$500.00$15,000$182,500

Strengths & weaknesses

Where it shines

  • GPQA: 87.7 (rank #1 of 29, top tier)
  • MATH: 96.7 (rank #3 of 29, top tier)
  • Arena: 1380 (rank #4 of 27, top tier)

Where it lags

No clear weaknesses across published benchmarks.

Best alternatives

The closest models to o3 by tier and benchmark score:

ModelScore$ in / outContextAction
Grok 4
xAI
83.6 $3.00 / $15.00 256k Try → · vs o3
Claude Opus 4.1
Anthropic
83.6 $15.00 / $75.00 200k Try → · vs o3
GPT-5
OpenAI
86.0 $1.25 / $10.00 400k Try → · vs o3
Gemini 2.5 Pro
Google
80.9 $1.25 / $10.00 2M Try → · vs o3
o1
OpenAI
75.7 $15.00 / $60.00 200k Try → · vs o3

Frequently asked questions

Is o3 a good model?

o3 scores 83.7 on the llmrank.top composite (rank #2 of 30). It is in the top tier (the leader, GPT-5, scores 86.0). Whether it's the right fit depends on your workload — see the use-case discussion on this page.

How much does o3 cost?

o3 is priced at $2.00 per 1M input tokens and $8.00 per 1M output tokens (USD). For a 10M-token-per-day workload split 50/50, that works out to roughly $50.00/day or $18,250/year.

What is o3's context window?

200k tokens. That covers most multi-document workloads.

Is o3 open source?

No — it is a closed (proprietary) model accessed only via the provider API.

What is o3's SWE-Bench score?

o3 scores 71.7% on SWE-Bench Verified — the benchmark that measures real-world GitHub issue resolution. Its Chatbot Arena Elo is 1380.

What are the best alternatives to o3?

Closest alternatives by tier and score: Grok 4, Claude Opus 4.1, GPT-5. See the alternatives section on this page for side-by-side numbers.


Related: Grok 4 · Claude Opus 4.1 · GPT-5 · Full leaderboard

Spotted out-of-date numbers? Open an issue — corrections usually ship within 24h.

Try o3 now

Direct link to the official playground — or use OpenRouter to A/B test it against any other model on a single API key.

Open OpenAI playground → Try via OpenRouter →