Skip to main content

Model comparison

o3 vs Sarvam 30B

Data verified

Head-to-head evidence from 12 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

OpenAI
47.84/100
Margin
7.3pts
← winning
40.53/100
0 category wins0 category wins

Public leaderboard positions: o3 #129 (Supported); Sarvam 30B #167 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. o3 and Sarvam 30B share 12 comparable benchmark results. 0 of 8 categories are comparable. 5 results are unique to o3; 0 to Sarvam 30B.

Updated July 17, 2026
Shared results
12
o3 only
5
Sarvam 30B only
0
Comparable categories
0 / 8

Benchmark data for o3 and Sarvam 30B is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

o3 is priced at $2.00 input / $8.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Sarvam 30B. o3 has the larger context window at 200K, compared with 64K for Sarvam 30B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for o3 and Sarvam 30B
Categoryo3ΔSarvam 30B
Matho314.5MarginNo overlapSarvam 30BNot measured

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

Metrico3Sarvam 30BComparison
Input / output priceUSD per 1M tokenso3$2 input / $8 outputSarvam 30B$0 input / $0 outputSarvam 30B has the lower combined listed price.
Generation speedtokens per secondo3118 tok/sSarvam 30BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokeno35.38 sSarvam 30BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokenso3200KSarvam 30B64Ko3 lists the larger context window.

Benchmark Deep Dive

Agentic
Benchmarko3Sarvam 30BResult
τ²-bench resultsSource 80.7%34.5%o3 leads
Coding
Benchmarko3Sarvam 30BResult
Terminal-Bench HardSource 37.1%2.3%o3 leads
AA-SciCodeSource 41.0%19.2%o3 leads
Reasoning
Benchmarko3Sarvam 30BResult
AA-LCRSource 69.3%0.0%o3 leads
CritPtSource 1.1%0.3%o3 leads
Knowledge
Benchmarko3Sarvam 30BResult
Artificial Analysis Intelligence IndexSource 30.4%6.6%o3 leads
AA-GPQA DiamondSource 82.7%63.3%o3 leads
AA-HLESource 20.0%7.0%o3 leads
AA-Omniscience IndexSource -15.3%-72.0%o3 leads
AA-Omniscience AccuracySource 38.4%12.7%o3 leads
AA-Omniscience Hallucination RateSource 87.1%97.0%o3 leads
Math
Benchmarko3Sarvam 30BResult
AA MATH-500Source 99.2%Not comparable
FrontierMath v2 (Tiers 1-3)Source 18.685%Not comparable
FrontierMath v2 (Tier 4)Source 2.083%Not comparable
Multimodal
Benchmarko3Sarvam 30BResult
AA-MMMU-ProSource 70.1%Not comparable
Design Arena WebsiteSource 1071Not comparable
Inst. Following
Benchmarko3Sarvam 30BResult
AA-IFBenchSource 71.4%26.5%o3 leads
Frequently Asked Questions (3)

Can I compare o3 and Sarvam 30B on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for o3 and Sarvam 30B today?

o3: $2.00 input / $8.00 output per 1M tokens Sarvam 30B: $0.00 input / $0.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Related Comparisons

Last updated: July 17, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.